feat(typescript): add MCP security scanner and lifecycle management to TS SDK by imran-siddique · Pull Request #947 · microsoft/agent-governance-toolkit

imran-siddique · 2026-04-12T03:38:15Z

Summary

Adds two new modules to the TypeScript SDK:

MCP Security Scanner (mcp.ts)

Detects tool poisoning (prompt-injection patterns, encoded payloads)
Detects typosquatting (Levenshtein distance check against known tools)
Detects hidden instructions (zero-width Unicode chars, homoglyphs)
Detects rug pull (anomalously long descriptions with instruction patterns)
Risk scoring (0-100) with severity-weighted aggregation

Lifecycle Manager (lifecycle.ts)

Full state machine: provisioning → active → suspended/rotating/degraded/quarantined → decommissioning → decommissioned
Enforced valid transitions (invalid throws)
Ordered event log with agent_id, timestamps, and initiator tracking
Convenience methods: �ctivate(), suspend(), quarantine(), decommission()

Tests

39 tests covering all 4 threat types, safe tool scanning, valid/invalid transitions, event logging

Other

Updated index.ts barrel exports
Updated README.md with API docs for both modules

Co-authored-by: Copilot [email protected]

github-actions · 2026-04-12T03:38:45Z

🤖 AI Agent: security-scanner — Security Analysis of the Pull Request

Security Analysis of the Pull Request

This pull request introduces two new modules to the TypeScript SDK: McpSecurityScanner and LifecycleManager. Both modules are critical to the security and governance of AI agents, and as such, require a thorough security review. Below is an analysis of potential vulnerabilities and recommendations for improvement.

1. Prompt Injection Defense Bypass

Finding: 🔴 CRITICAL

The McpSecurityScanner module attempts to detect prompt injection patterns in tool descriptions using predefined regular expressions (POISONING_PATTERNS). However, the detection logic is limited to a fixed set of patterns, which makes it susceptible to bypasses through obfuscation techniques such as:

Using synonyms or rephrased instructions (e.g., "ignore all prior" instead of "ignore previous").
Using non-standard Unicode characters or encoding (e.g., Base64, HTML entities).
Using concatenation or splitting of malicious instructions (e.g., "ig" + "nore previous").

Attack Vector:

An attacker could craft a malicious tool description that bypasses the current pattern-matching logic by using obfuscation techniques, leading to successful prompt injection attacks.

Recommendation:

Implement a more robust natural language processing (NLP)-based approach to detect semantic intent rather than relying solely on regular expressions.
Use a pre-trained language model to identify suspicious patterns or intent in tool descriptions.
Add a mechanism to detect and decode common encoding schemes (e.g., Base64, HTML entities) before scanning for patterns.
Regularly update the list of patterns and detection logic to account for new attack techniques.

2. Policy Engine Circumvention

Finding: 🟠 HIGH

The LifecycleManager enforces valid state transitions using a predefined state machine (VALID_TRANSITIONS). However, the transition() method does not validate the initiated_by parameter. This could allow unauthorized users or processes to manipulate the lifecycle state by providing arbitrary values for initiated_by.

Attack Vector:

An attacker with access to the LifecycleManager instance could call the transition() method directly and provide a forged initiated_by value, potentially bypassing access controls or audit mechanisms.

Recommendation:

Add a validation mechanism to ensure that the initiated_by parameter is an authorized entity.
Consider integrating with an authentication/authorization system to verify the identity of the initiator.
Log additional metadata (e.g., IP address, session ID) to improve auditability.

3. Trust Chain Weaknesses

Finding: 🔵 LOW

No explicit trust chain validation (e.g., SPIFFE/SVID, certificate pinning) is implemented in this pull request. However, this is not directly relevant to the changes introduced in this PR, as the modules do not handle certificate-based authentication or trust delegation.

Recommendation:

Ensure that any future changes to the SDK that involve trust chains (e.g., agent authentication) include robust validation mechanisms, such as SPIFFE/SVID or certificate pinning.

4. Credential Exposure

Finding: 🔵 LOW

There is no evidence of sensitive information (e.g., credentials, API keys) being logged or exposed in this pull request. However, the LifecycleManager logs events, including the initiated_by field, which could potentially contain sensitive information if not sanitized.

Recommendation:

Ensure that the initiated_by field is sanitized before logging to prevent accidental exposure of sensitive information.
Add a warning in the documentation to avoid including sensitive data in the initiated_by field.

5. Sandbox Escape

Finding: 🔵 LOW

The changes in this pull request do not introduce any new code that interacts with the operating system or external processes. As such, there is no immediate risk of a sandbox escape.

Recommendation:

Ensure that any future changes involving execution of external commands or scripts are sandboxed and validated to prevent potential escapes.

6. Deserialization Attacks

Finding: 🔵 LOW

The McpSecurityScanner and LifecycleManager modules do not perform any deserialization of untrusted data. Therefore, there is no immediate risk of deserialization attacks.

Recommendation:

If future changes involve deserialization of user-provided data (e.g., JSON, YAML), ensure that the deserialization process is secure and does not allow arbitrary code execution.

7. Race Conditions

Finding: 🟡 MEDIUM

The LifecycleManager class does not include any explicit locking or synchronization mechanisms. If multiple threads or processes access the same LifecycleManager instance concurrently, it could lead to race conditions, resulting in invalid state transitions or inconsistent event logs.

Attack Vector:

An attacker could exploit race conditions to force invalid state transitions or corrupt the event log, potentially bypassing lifecycle policies.

Recommendation:

Implement thread-safe mechanisms (e.g., locks or atomic operations) to ensure that state transitions and event logging are atomic and consistent.
Consider using a library like async-mutex for managing concurrency in JavaScript/TypeScript.

8. Supply Chain Risks

Finding: 🟠 HIGH

The pull request does not include a package-lock.json or yarn.lock file, which makes it difficult to verify the integrity of the dependencies. Additionally, the McpSecurityScanner relies on a hardcoded list of known tool names (KNOWN_TOOL_NAMES) for typosquatting detection, which could be incomplete or outdated.

Attack Vector:

Dependency confusion or typosquatting attacks could occur if malicious packages with similar names are introduced into the dependency tree.
The hardcoded list of known tool names may not cover all legitimate tools, leading to false positives or missed detections.

Recommendation:

Include a package-lock.json or yarn.lock file to lock dependency versions and reduce the risk of supply chain attacks.
Regularly update the list of known tool names to include new tools as they are added to the ecosystem.
Consider integrating with a centralized registry or API to fetch the latest list of known tools dynamically.

Additional Observations

Error Handling in McpSecurityScanner:
The detectToolPoisoning method silently ignores errors during URL decoding. While this is not a direct vulnerability, it could lead to missed detections. Consider logging or handling these errors explicitly.
Testing Coverage:
The test coverage for both modules appears to be comprehensive, with tests for valid/invalid transitions, event logging, and various threat detection scenarios. However, additional tests for edge cases (e.g., extremely large tool descriptions, unusual Unicode characters) would be beneficial.
Documentation:
The documentation for both modules is clear and provides examples of usage. However, it would be helpful to include a note about the limitations of the current threat detection logic and the importance of keeping the tool name list up to date.

Summary of Findings and Recommendations

Finding	Severity	Recommendation
Prompt injection defense bypass	🔴 CRITICAL	Use NLP-based detection, handle obfuscation techniques, and update patterns regularly.
Policy engine circumvention	🟠 HIGH	Validate `initiated_by` parameter and integrate with an authentication/authorization system.
Trust chain weaknesses	🔵 LOW	No immediate issues, but ensure robust validation for future trust chain features.
Credential exposure	🔵 LOW	Sanitize `initiated_by` field before logging.
Sandbox escape	🔵 LOW	No immediate issues, but ensure sandboxing for future OS/process interactions.
Deserialization attacks	🔵 LOW	No immediate issues, but ensure secure deserialization for future changes.
Race conditions	🟡 MEDIUM	Add thread-safe mechanisms to `LifecycleManager` for state transitions and event logging.
Supply chain risks	🟠 HIGH	Include `package-lock.json` or `yarn.lock` and dynamically update the list of known tool names.

Final Recommendation: Request Changes

While the new modules provide valuable functionality, the critical vulnerabilities in prompt injection detection and the potential for policy circumvention necessitate changes before merging. Addressing these issues will ensure the security and reliability of the toolkit for downstream users.

github-actions

🤖 AI Agent: code-reviewer

Review Summary

This pull request introduces two new modules to the TypeScript SDK: the MCP Security Scanner and the Lifecycle Manager, along with supporting documentation and tests. The MCP Security Scanner focuses on detecting security threats in tool definitions, while the Lifecycle Manager enforces valid state transitions for agents and maintains an event log. Both modules are well-documented and include comprehensive test coverage.

Below is a detailed review of the changes, focusing on the specified areas of concern.

🔴 CRITICAL: Security Issues

1. MCP Security Scanner: Unicode Homoglyph Detection

The homoglyph detection logic in mcp.ts only maps a limited set of Cyrillic and Greek characters to their Latin equivalents. This approach is insufficient for comprehensive detection of homoglyph-based attacks, as it does not account for other Unicode scripts (e.g., Armenian, Georgian, or extended Latin).
Impact: Attackers could bypass detection by using homoglyphs not included in the map.
Actionable Fix: Expand the homoglyph map to include a broader range of Unicode characters or use a library like unicode-slugify for robust normalization.

2. Lifecycle Manager: Lack of Authorization Checks

The LifecycleManager allows state transitions without verifying the identity or authorization of the initiator (initiatedBy field). This could allow unauthorized users or systems to manipulate agent states.
Impact: Unauthorized state changes could lead to security breaches, such as prematurely activating or decommissioning agents.
Actionable Fix: Implement an authorization layer to validate initiatedBy against a trusted identity provider (e.g., SPIFFE/SVID).

3. MCP Security Scanner: Risk Scoring

The risk scoring mechanism aggregates threat severity but does not account for the cumulative impact of multiple threats. For example, a tool definition with multiple "low" severity threats could still pose a significant risk.
Impact: Risk scores may underestimate the actual threat level, leading to potential security bypass.
Actionable Fix: Use a weighted scoring system that accounts for the number of threats and their severity.

🟡 WARNING: Potential Breaking Changes

1. Lifecycle Manager API

The LifecycleManager enforces strict state transitions, which could break existing integrations if they rely on invalid transitions. For example, transitioning directly from Provisioning to Suspended would now throw an error.
Impact: Existing systems using the SDK may encounter runtime errors if they attempt invalid transitions.
Actionable Fix: Clearly document the state machine and provide migration guides for users upgrading to this version.

2. Index.ts Barrel Exports

The addition of new exports (McpSecurityScanner, LifecycleManager) to index.ts changes the public API of the SDK. This could lead to unexpected behavior for users relying on specific imports.
Impact: Users may encounter conflicts or unexpected behavior if they have custom implementations of similarly named classes.
Actionable Fix: Use semantic versioning and communicate these changes in release notes.

💡 Suggestions for Improvement

1. Thread Safety

The LifecycleManager does not appear to be thread-safe. Concurrent calls to transition() could lead to race conditions, especially in multi-threaded environments.
Suggestion: Use locks or atomic operations to ensure thread safety.

2. Type Safety

The LifecycleManager uses string literals for reason and initiatedBy. These could benefit from stricter type definitions (e.g., enums or validated strings).
Suggestion: Introduce stricter type validation for these fields.

3. Backward Compatibility

Consider adding deprecation warnings for any features or APIs that are being replaced or modified in this update.
Suggestion: Use feature flags or versioned APIs to ease migration.

4. OWASP Agentic Top 10 Compliance

While the documentation claims full compliance with OWASP Agentic Top 10, it would be beneficial to include automated tests or verification scripts to validate compliance during CI/CD.
Suggestion: Add OWASP compliance checks as part of the test suite.

5. Documentation

The documentation for the MCP Security Scanner could include examples of real-world attack scenarios and how the scanner mitigates them.
Suggestion: Expand the README with detailed use cases and threat modeling examples.

Final Recommendations

Merge Blockers: Address the critical security issues (homoglyph detection, authorization checks, risk scoring) before merging.
Post-Merge Actions: Communicate breaking changes clearly in release notes and provide migration guides.
Future Enhancements: Focus on thread safety, type validation, and expanding security coverage.

This pull request introduces valuable functionality but requires additional security hardening and backward compatibility considerations.

…o TS SDK Co-authored-by: Copilot <[email protected]>

github-actions

🤖 AI Agent: code-reviewer

Pull Request Review: feat(typescript): add MCP security scanner and lifecycle management to TS SDK

🔴 CRITICAL: Security Issues

Tool Poisoning Detection - Incomplete Coverage:
- The detectToolPoisoning method in McpSecurityScanner does not account for variations of encoded payloads beyond percent-encoding (e.g., Base64, HTML entities). Attackers could bypass detection by using alternate encoding schemes.
- Action: Extend detection logic to decode and analyze Base64, HTML entities, and other common encoding formats.
Hidden Instructions - Homoglyph Detection:
- The homoglyph detection logic in detectHiddenInstructions is limited to predefined mappings. This leaves room for attackers to use other Unicode homoglyphs not covered by the current map.
- Action: Integrate a comprehensive Unicode homoglyph library or use an external package to ensure broader coverage.
Lifecycle Manager - Quarantine State:
- The quarantine method in LifecycleManager does not enforce additional security measures (e.g., disabling sensitive operations or isolating the agent). This could allow compromised agents to continue executing harmful actions.
- Action: Implement stricter controls when transitioning to the Quarantined state, such as revoking permissions or halting execution.

🟡 WARNING: Potential Breaking Changes

LifecycleManager API:
- The addition of enforced state transitions and event logging introduces stricter constraints on agent lifecycle management. Existing integrations may fail if they attempt invalid transitions.
- Action: Clearly document the new state machine and provide migration guidance for users of the SDK.
McpSecurityScanner API:
- The scan and scanAll methods return a new McpScanResult structure. This could break compatibility for users expecting simpler outputs.
- Action: Ensure backward compatibility by providing a legacy mode or adapter for older integrations.

💡 Suggestions for Improvement

Risk Scoring Granularity:
- The risk scoring mechanism in McpSecurityScanner aggregates severity weights but does not differentiate between threat types. For example, ToolPoisoning should likely carry a higher weight than Typosquatting.
- Action: Introduce threat-specific weighting to improve risk assessment accuracy.
Thread Safety in LifecycleManager:
- The LifecycleManager class does not appear to be thread-safe. Concurrent transitions could lead to race conditions or inconsistent states.
- Action: Add synchronization mechanisms (e.g., locks or atomic operations) to ensure thread safety.
OWASP Agentic Top 10 Compliance:
- While the MCP Security Scanner addresses several threats, it does not explicitly cover all OWASP Agentic Top 10 risks (e.g., agent impersonation or trust boundary violations).
- Action: Map the scanner's capabilities to OWASP Agentic Top 10 and address any gaps.
Testing Coverage:
- While the tests for LifecycleManager and McpSecurityScanner are comprehensive, edge cases (e.g., malformed tool definitions or simultaneous transitions) are not covered.
- Action: Add tests for edge cases and concurrency scenarios.
Documentation:
- The README provides basic usage examples but lacks detailed explanations of the risk scoring algorithm, state machine transitions, and threat detection logic.
- Action: Expand documentation to include detailed explanations and diagrams for better developer understanding.

Summary of Actions

🔴 Address critical security gaps in encoding detection, homoglyph coverage, and quarantine state handling.
🟡 Mitigate potential breaking changes by documenting migration paths and providing backward compatibility.
💡 Enhance risk scoring, thread safety, testing coverage, and documentation for improved usability and robustness.

This pull request introduces valuable features but requires additional work to ensure security, compatibility, and usability.

Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]>

Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]>

* feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (microsoft#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (microsoft#950) Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (microsoft#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (microsoft#954) Closes microsoft#952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (microsoft#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (microsoft#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (microsoft#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (microsoft#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (microsoft#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (microsoft#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from microsoft#772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (microsoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (microsoft#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (microsoft#908) 15 curated ATR detection rules + sync script. Closes microsoft#901. * fix(docs): correct npm package name and stale version refs across 21 files (microsoft#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (microsoft#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (microsoft#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (microsoft#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (microsoft#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (microsoft#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (microsoft#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]>

…1017) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]>

* feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]>

* fix(pipeline): run NuGet ESRP signing on Windows agent (microsoft#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs microsoft#1017 and microsoft#1020 (microsoft#1125) PRs microsoft#1017 and microsoft#1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR microsoft#1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR microsoft#1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (microsoft#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (microsoft#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (microsoft#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (microsoft#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (microsoft#950) Reflects new capabilities added in PRs microsoft#947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (microsoft#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (microsoft#954) Closes microsoft#952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (microsoft#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (microsoft#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (microsoft#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (microsoft#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (microsoft#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (microsoft#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from microsoft#772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (microsoft#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (microsoft#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (microsoft#908) 15 curated ATR detection rules + sync script. Closes microsoft#901. * fix(docs): correct npm package name and stale version refs across 21 files (microsoft#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (microsoft#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (microsoft#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (microsoft#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (microsoft#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (microsoft#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (microsoft#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (microsoft#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (microsoft#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (microsoft#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (microsoft#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (microsoft#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (microsoft#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (microsoft#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (microsoft#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (microsoft#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (microsoft#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (microsoft#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (microsoft#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (microsoft#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (microsoft#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

…#1166) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs #1017 and #1020 (#1125) PRs #1017 and #1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR #1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR #1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

…) + critic gap docs (#1170) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs #1017 and #1020 (#1125) PRs #1017 and #1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR #1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR #1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

…1192) * feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs #1017 and #1020 (#1125) PRs #1017 and #1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR #1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR #1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): fix lint errors and remove pi-mono breaking dep scan Two CI failures on main: 1. lint (agent-compliance): W293/W292 trailing whitespace and missing newlines in agt.py and verify.py — fixed. 2. dependency-scan: pi-mono-agentmesh references unregistered npm packages — removed entire pi-mono integration that was merged from draft PR #970 without proper review. Co-authored-by: Copilot <[email protected]> * feat: add AgentMesh component container images and GHCR publishing Add FastAPI server entrypoints for all four AgentMesh components: - trust-engine (port 8443): Agent identity verification, IATP handshakes - policy-server (port 8444): Governance policy evaluation from YAML/JSON - audit-collector (port 8445): Merkle-chained audit logging with persistence - api-gateway (port 8446): Reverse proxy with per-agent rate limiting Infrastructure: - Single Dockerfile with COMPONENT build arg (non-root, tini, health checks) - GitHub Actions workflow for GHCR publishing (multi-arch amd64/arm64) - Helm chart updated to reference ghcr.io/microsoft/agentmesh/* images - 28 integration tests covering all server endpoints Resolves the missing container images that blocked full AgentMesh cluster deployment (images were referenced in Helm chart but never built). Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

* feat(dotnet): add MCP security namespace — completes cross-language MCP parity * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: add Entra Agent ID bridge tutorial (Tutorial 31) (#10) * fix(pipeline): run NuGet ESRP signing on Windows agent (#1022) The EsrpCodeSigning@5 task constructs internal paths (batchSignPolicyFile, ciPolicyFile) using Windows-style backslashes. Running on ubuntu-latest produced garbled mixed paths like '/home/vsts/work/1/s/src\myapp\'. Changes: - Add per-job pool override: PublishNuGet runs on windows-latest - Convert FolderPath and all shell commands to Windows paths - Replace bash scripts with PowerShell for the Windows agent - PyPI and npm stages remain on ubuntu-latest (unchanged) - Add comment to delete orphaned ESRP_DOMAIN_TENANT_ID ADO variable Co-authored-by: Copilot <[email protected]> * docs: reland empty-merge changes from PRs #1017 and #1020 (#1125) PRs #1017 and #1020 were squash-merged as empty commits (0 file changes). This commit re-applies the intended documentation updates. From PR #1017 (critic gaps): - LIMITATIONS.md: add sections 7 (knowledge governance gap), 8 (credential persistence gap), 9 (initialization bypass risk) - LIMITATIONS.md: add knowledge governance and enforcement infra rows to 'What AGT Is Not' table - THREAT_MODEL.md: add knowledge flow and credential persistence to residual risks, add configuration bypass vectors table, remove stale '10/10' qualifier From PR #1020 (SOC2 resolved gaps): - soc2-mapping.md: mark kill switch as resolved (saga handoff implemented in kill_switch.py:69-178) - soc2-mapping.md: mark DeltaEngine verify_chain() as resolved (SHA-256 chain verification in delta.py:67-127) - soc2-mapping.md: add Resolved section to gaps summary, update Processing Integrity to 2 of 4 defects (was 3 of 4) Co-authored-by: Copilot <[email protected]> * feat(dotnet): add MCP security namespace — completes cross-language MCP parity (#1021) * fix(ci): add path filters and concurrency; announce v3.1.0 release CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 * docs: update SOC2 mapping for resolved kill switch and DeltaEngine gaps - Kill switch is no longer placeholder: now implements saga handoff with handoff_success_count tracking (kill_switch.py:69-178) - DeltaEngine verify_chain() is no longer a stub: now performs SHA-256 chain verification (delta.py:67-127) - Move both from Critical/High gaps to new 'Resolved' section - Update Processing Integrity coverage (2 of 4 defects, not 3 of 4) - Update evidence table with current line ranges * feat(dotnet): add MCP security namespace with scanner, gateway, redactor, and sanitizer Add AgentGovernance.Mcp namespace implementing full MCP security parity with TypeScript and Rust SDKs: - McpSecurityScanner: tool poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, and description injection detection - McpCredentialRedactor: regex-based redaction of API keys, bearer tokens, connection strings, and secret assignments - McpResponseSanitizer: response scanning for prompt injection tags, imperative phrasing, credential leakage, and exfiltration URLs - McpGateway: policy enforcement pipeline with deny/allow lists, payload sanitization, rate limiting, and human approval gates Includes 46 xUnit tests covering all threat categories. Updates SDK-FEATURE-MATRIX.md to flip .NET MCP Security from — to ✅. --------- Co-authored-by: Copilot <[email protected]> * docs: address external critic gaps (#1025) * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#5) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add 26 xUnit tests - Update README Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#6) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#7) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code (#8) * feat(openshell): add governance skill package and runnable example (#942) Co-authored-by: Copilot <[email protected]> * feat(typescript): add MCP security scanner and lifecycle management to TS SDK (#947) Co-authored-by: Copilot <[email protected]> * docs: update SDK feature matrix after parity pass (#950) Reflects new capabilities added in PRs #947 (TS), .NET, Rust, Go: - TypeScript: MCP security scanner + lifecycle management (was 5/14, now 7/14) - .NET: Kill switch + lifecycle management (was 8/14, now 10/14) - Rust: Execution rings + lifecycle management (was 6/14, now 8/14) - Go: MCP security + rings + lifecycle (was 4/14, now 7/14) All SDKs now have lifecycle management. Core governance (policy, identity, trust, audit) + lifecycle = 5 primitives shared across all 5 languages. Co-authored-by: Copilot <[email protected]> * docs: add LIMITATIONS.md - honest design boundaries and layered defense (#953) Addresses valid external critique of AGT's architectural blind spots: 1. Action vs Intent: AGT governs individual actions, not reasoning or action sequences. Documents the compound-action gap explicitly and recommends content policies + model safety layers. 2. Audit logs record attempts, not outcomes: Documents that post-action state verification is the user's responsibility today, with hooks planned. 3. Performance honesty: README now notes that <0.1ms is policy-eval only; distributed mesh adds 5-50ms. Full breakdown in LIMITATIONS.md. 4. Complexity spectrum: Documents the minimal path (just PolicyEvaluator, no mesh/crypto) vs full enterprise stack. 5. Vendor independence: Documents zero cloud dependencies in core, standard formats for all state, migration path. 6. Recommended layered defense architecture diagram showing AGT as one layer alongside model safety, application logic, and infrastructure. Co-authored-by: Copilot <[email protected]> * fix(docs): rewrite OpenClaw sidecar deployment with working K8s manifests (#954) Closes #952 Co-authored-by: Copilot <[email protected]> * feat: reversibility checker, trust calibration guide, escalation tests (#955) ReversibilityChecker with 4 levels and compensation plans. Trust score calibration guide with weights, decay, thresholds. 19 tests. Co-authored-by: Copilot <[email protected]> * feat: AGT Lite — zero-config governance in 3 lines + fix broken quickstart (#956) agent_os.lite: govern() factory, sub-ms enforcement, 16 tests. Fixed quickstart that called nonexistent add_rules(). Co-authored-by: Copilot <[email protected]> * fix: bump all runtime versions to 3.1.0 and fix CI lint/test failures (#957) - Bump __version__ in 29 Python __init__.py files from 3.0.2 to 3.1.0 - Bump version= in 6 setup.py files from 3.0.2 to 3.1.0 - Bump meter version strings in _mcp_metrics.py - Bump 9 package.json files from 3.0.2 to 3.1.0 - Bump .NET csproj Version from 3.0.2 to 3.1.0 - Bump Rust workspace Cargo.toml from 3.0.2 to 3.1.0 - Create Go sdk doc.go with version marker 3.1.0 - Fix ruff W292 (missing newline at EOF) in data_classification.py - Fix CLI init regex to allow dots in agent names (test_init_special_characters) Co-authored-by: Copilot <[email protected]> * fix(openclaw): critical honesty pass — document what works vs what's planned (#958) Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging - use workspace root with -p agentmesh (#959) * fix(openclaw): critical honesty pass — document what works vs what's planned Server (__main__.py): - Add --host/--port argparse + env var support (was hardcoded 127.0.0.1:8080) Dockerfile.sidecar: - Copy modules/ directory (was missing, causing build failure) - Use 0.0.0.0 for container binding (127.0.0.1 is wrong inside containers) - Remove phantom port 9091 (no separate metrics listener exists) openclaw-sidecar.md — full honesty rewrite: - Add status banner: transparent interception is NOT yet implemented - Document actual sidecar API endpoints (health, detect/injection, execute, metrics) - Fix Docker Compose to use Dockerfile.sidecar (was using wrong Dockerfile) - Remove GOVERNANCE_PROXY claim (OpenClaw doesn't natively read this) - Replace fictional SLO/Grafana sections with real /api/v1/metrics docs - Add Roadmap section listing what's planned vs shipped openshell.md: - Remove references to non-existent shell scripts - Fix python -m agentmesh.server to python -m agent_os.server - Add note that sidecar doesn't transparently intercept (must call API) - Replace pip install agentmesh-platform with Python skill library usage Co-authored-by: Copilot <[email protected]> * fix(ci): fix Rust crate packaging — use workspace root with -p agentmesh cargo package in a workspace writes .crate files to the workspace root's target/package/, not the individual crate's directory. The pipeline was running from the crate subdirectory and couldn't find the output. Fix: change workingDirectory from packages/agent-mesh/sdks/rust/agentmesh to packages/agent-mesh/sdks/rust (workspace root) and add -p agentmesh to all cargo commands to target the specific crate. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * docs(adr): ADR 0005 — Liveness attestation extension for TrustHandshake (#948) Proposes liveness attestation as opt-in gate for TrustHandshake. Addresses ghost-agent and ungraceful-handoff gaps from #772. Co-authored-by: kevinkaylie <[email protected]> * blog: MCP Security — Why Your AI Agent Tool Calls Need a Firewall (#899) Co-authored-by: aymenhmaidiwastaken <[email protected]> * feat: add LotL prevention policy for security measures (#949) YAML policy template for Living-off-the-Land detection and prevention. * feat(examples): add ATR community security rules for PolicyEvaluator (#908) 15 curated ATR detection rules + sync script. Closes #901. * fix(docs): correct npm package name and stale version refs across 21 files (#960) - Fix @agentmesh/sdk → @microsoft/agentmesh-sdk in 13 markdown files (README, QUICKSTART, tutorials, SDK docs, i18n, changelog) - Fix broken demo path in agent-os README (agent-os/demo.py → demo/maf_governance_demo.py) - Remove stale v1.0.0 labels from extension status table - Bump AGT Version refs 3.0.2 → 3.1.0 in case study templates and ATF conformance assessment Co-authored-by: Copilot <[email protected]> * fix(ci): use ESRP Release for NuGet signing (#961) Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing (#962) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): add missing packages to ESRP pipeline and fix Go version tag (#963) * fix(ci): add missing packages to ESRP pipeline and fix Go version tag Three gaps found during publish verification: 1. PyPI: add agentmesh-marketplace (8th package, was missing from matrix) 2. Rust: build+publish both workspace crates (agentmesh + agentmesh-mcp) - Changed from single-crate to workspace build (--workspace) - Package loop builds both .crate files - Renamed artifact from 'rust-agentmesh' to 'rust-crates' 3. Go: add 'v' prefix to version in doc.go (3.1.0 → v3.1.0) - Go module tags require semver with v prefix - Pipeline grep expects '// Version: v...' format Co-authored-by: Copilot <[email protected]> * fix(ci): correct ESRP NuGet contenttype casing — 'NuGet' not 'Nuget' ESRP Release rejected 'Nuget' with: 'The value provided for ReleaseContentType property is invalid.' ErrorCode 2254. ESRP content types are case-sensitive. Fix: 'Nuget' -> 'NuGet'. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(ci): use EsrpCodeSigning + dotnet push for NuGet (#965) EsrpRelease@11 does not support NuGet as a contenttype — it's for PyPI/npm/Maven/crates.io package distribution. NuGet packages must be signed with EsrpCodeSigning@5 first, then pushed with dotnet nuget push. New flow: 1. EsrpCodeSigning@5 with NuGetSign + NuGetVerify operations (CP-401405) 2. dotnet nuget push with the signed .nupkg to nuget.org This matches the standard Microsoft NuGet ESRP signing pattern used by azure-sdk, dotnet runtime, and other Microsoft OSS projects. Co-authored-by: Copilot <[email protected]> * fix(security): upgrade axios to 1.15.0 - CVE-2026-40175, CVE-2025-62718 (#966) Critical S360 action items for SFI-ES5.2 1ES Open Source Vulnerabilities. CVE-2026-40175 (CVSS 9.9): Unrestricted Cloud Metadata Exfiltration via Header Injection Chain — prototype pollution gadget enables CRLF injection in HTTP headers, bypassing AWS IMDSv2 session tokens. CVE-2025-62718: NO_PROXY Bypass via Hostname Normalization — trailing dots and IPv6 literals skip NO_PROXY matching, enabling SSRF through attacker-controlled proxy. Upgraded in 3 packages: - extensions/copilot: 1.14.0 → 1.15.0 - extensions/cursor: 1.13.5 → 1.15.0 - agent-os-vscode: 1.13.6 → 1.15.0 Co-authored-by: Copilot <[email protected]> * fix(ci): resolve ESRP_DOMAIN_TENANT_ID cyclical reference (#967) The ADO variable ESRP_DOMAIN_TENANT_ID had a cyclical self-reference, preventing ESRP authentication across ALL publishing stages (PyPI, npm, NuGet, crates.io). Fix: Define MICROSOFT_TENANT_ID as a pipeline-level variable with the well-known Microsoft corporate tenant ID (72f988bf-..., same default used by ESRP Release action.yml). This is a public value, not a secret. Also: NuGet publishing requires Microsoft as co-owner of the package on NuGet.org. See https://aka.ms/Microsoft-NuGet-Compliance Co-authored-by: Copilot <[email protected]> * docs: sync audit redaction status and framing with current code - Update SOC2 mapping to reflect CredentialRedactor now redacts credential-like secrets before audit persistence (API keys, tokens, JWTs, connection strings, etc.). Remaining gap: non-credential PII (email, phone, addresses) not yet redacted in audit entries. - Replace 'kernel-level enforcement' with 'policy-layer enforcement' in README, OWASP compliance, and architecture overview to match the existing 'application-level governance' framing in README Security section and LIMITATIONS.md. - Qualify 10/10 OWASP coverage claim in COMPARISON.md with footnote clarifying this means mitigation components exist per risk category, not full elimination. - Update owasp-llm-top10-mapping.md LLM06 row for credential redaction. Addresses doc/code inconsistencies identified in external review. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> * fix(lint): resolve agent-mesh lint errors in eu_ai_act.py (#1028) - Remove unused variable profiling_override (F841) - Remove f-string without placeholders (F541) - Fix whitespace in docstrings (W293) Co-authored-by: Copilot <[email protected]> * fix(ci): add path filters and concurrency; announce v3.1.0 release (#1039) CI optimization: - Add paths-ignore for docs to 5 code-only workflows - Add paths filter to Link Check (only run on docs changes) - Add concurrency groups to 7 heavy workflows - Docs-only PRs drop from ~14 checks to ~4 README: - Add v3.1.0 release announcement callout - Add PyPI version badge - Update tutorial count to 31 Co-authored-by: Copilot <[email protected]> * docs: add ADOPTERS.md and make deployment guides multi-cloud (#1040) - New ADOPTERS.md following Backstage/Flatcar pattern with Production, Evaluation, and Academic tables + instructions for adding your org - Rewrite docs/deployment/README.md from Azure-only to multi-cloud: Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose, self-hosted. Updated architecture diagram to show cloud-agnostic deployment patterns. - Fix broken AWS/GCP links (pointed to non-existent paths) - README now links to 'Deployment Guides' (multi-cloud) instead of 'Azure Deployment' - README Contributing section invites adopters to add their org Co-authored-by: Copilot <[email protected]> * feat: add AGT Lite — zero-config governance in 3 lines, fix broken quickstart (#1044) Addresses the #1 developer experience criticism: AGT is too complex to start. New: agent_os.lite — lightweight governance module - govern() factory: one line to create a governance gate - check(action): one line to enforce — raises GovernanceViolation or returns True - check.is_allowed(action): non-raising bool version - Allow lists, deny lists, regex patterns, content filtering, rate limiting - Built-in audit trail and stats - Sub-millisecond evaluation (0.003ms avg, 1000 evals in <100ms) - Zero dependencies beyond stdlib (re, time, datetime) - 16 tests passing Fix: govern_in_60_seconds.py quickstart - BROKEN: was calling PolicyEvaluator.add_rules() which does not exist - FIXED: now uses agent_os.lite.govern() which actually works - Verified end-to-end: script runs and produces correct output The lite module is for developers who just want basic governance without learning PolicyEvaluator, YAML, OPA/Rego, trust mesh, etc. Upgrade to the full stack when you need it. Co-authored-by: Copilot <[email protected]> * feat(ci): enhance weekly security audit with 7 new scan jobs (#1051) Add comprehensive security checks based on issues found during the MSRC-111178 security audit and ongoing post-merge reviews: - Workflow security regression (MSRC-111178 pull_request_target check) - Expression injection scan (github.event.* in run: blocks) - Docker security (root containers, wildcard CORS, hardcoded passwords, 0.0.0.0 bindings) - XSS and unsafe DOM (innerHTML, eval, yaml.load, shell=True) - Action SHA pinning compliance - Version pinning (pyproject.toml upper bounds, Docker :latest tags, license field format) - Dependency confusion with --strict mode (pyproject.toml + package.json) - Retention days updated to 180 (EU AI Act Art. 26(6)) Co-authored-by: Copilot <[email protected]> * fix(ci): fix OpenShell integration CI — spelling, link check, policy validation (#1057) - Add OpenShell/NVIDIA terms to cspell dictionary (Landlock, seccomp, syscall, etc.) - Fix broken link: openclaw-skill -> openshell-skill in docs/integrations/openshell.md - Fix policy validation: replace starts_with (invalid) with matches + regex Co-authored-by: Copilot <[email protected]> * feat: add reversibility checker, trust calibration guide, and escalation/reversibility tests (#1061) Addresses critical review feedback: 1. Rollback/reversibility (agent_os.reversibility) - ReversibilityChecker: pre-execution assessment of action reversibility - 4 levels: fully_reversible, partially_reversible, irreversible, unknown - CompensatingAction: structured undo plans for each action type - Built-in rules for 12 common actions (write, deploy, delete, email, etc.) - block_irreversible mode for strict environments 2. Trust score calibration guide (docs/security/trust-score-calibration.md) - Score component weights (compliance 35%, task 25%, behavior 25%, identity 15%) - Decay functions with tier floors - Initial score assignments by agent origin - Threshold recommendations (conservative/moderate/permissive) - Anti-gaming measures and operational playbook 3. Tests: 19 passing (10 escalation + 9 reversibility) Co-authored-by: Copilot <[email protected]> * feat: deployment runtime (Docker/AKS) and shared trust core types (#1062) agent-runtime: Evolve from thin re-export shim to deployment runtime - DockerDeployer: container deployment with security hardening (cap-drop ALL, no-new-privileges, read-only rootfs) - KubernetesDeployer: AKS pod deployment with governance sidecars (runAsNonRoot, seccompProfile, resource limits) - GovernanceConfig: policy/trust/audit config injected as env vars - DeploymentTarget protocol for extensibility (ADC, nono, etc.) - 24 tests (all subprocess calls mocked) agent-mesh: Extract shared trust types into agentmesh.trust_types - TrustScore, AgentProfile, TrustRecord, TrustTracker - Canonical implementations replacing ~800 lines of duplicated code across 6+ integration packages - 25 tests covering clamping, scoring, history, capabilities Co-authored-by: Copilot <[email protected]> * feat(dotnet): add kill switch and lifecycle management to .NET SDK (#1065) - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(go): add MCP security, execution rings, and lifecycle management to Go SDK (#1066) - mcp.go: MCP security scanner detecting tool poisoning, typosquatting, hidden instructions (zero-width chars, homoglyphs), and rug pulls - rings.go: Execution privilege ring model (Admin/Standard/Restricted/Sandboxed) with default-deny access control - lifecycle.go: Eight-state agent lifecycle manager with validated transitions - Full test coverage for all three modules - Updated README with API docs and examples Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK (#1067) * feat(dotnet): add kill switch and lifecycle management to .NET SDK - Add KillSwitch with arm/disarm, event history, and subscriber notifications - Add LifecycleManager with 8-state machine and validated transitions - Add comprehensive xUnit tests for both components (26 tests) - Update .NET SDK README with usage documentation Co-authored-by: Copilot <[email protected]> * feat(rust): add execution rings and lifecycle management to Rust SDK Add two new modules to the agentmesh Rust crate: - rings.rs: Four-level execution privilege ring model (Admin/Standard/ Restricted/Sandboxed) with per-agent assignment and per-ring action permissions, ported from the Python hypervisor enforcer. - lifecycle.rs: Eight-state agent lifecycle manager (Provisioning through Decommissioned) with validated state transitions and event history, matching the lifecycle model used across other SDK languages. Both modules include comprehensive unit tests and are re-exported from the crate root. README updated with API tables and usage examples. Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix: align lotl_prevention_policy.yaml with PolicyDocument schema The policy file used an incompatible schema format (id, parameter, regex_match, effect) instead of the expected PolicyDocument fields (name, condition.field, operator, action). This caused the validate-policies CI check to fail for all PRs. Changes: - id → name - condition.parameter → condition.field - operator: regex_match → operator: matches - action at rule level (shell_exec/file_read) → action: deny - effect: DENY → removed (redundant with action: deny) - Added version, name, description, disclaimer at top level Co-authored-by: Copilot <[email protected]> * fix: resolve .NET ESRP signing issues blocking NuGet publish GitHub Actions (publish.yml): - Fix broken if-guards on signing steps: env.ESRP_AAD_ID was set in step-level env (invisible to if-expressions). Replace with job-level ESRP_CONFIGURED env derived from secrets. - Add missing ESRP_CERT_IDENTIFIER to signing step env blocks. - Gate the publish step on ESRP_CONFIGURED so unsigned packages are never pushed to NuGet.org under the Microsoft.* prefix. - Make stub signing steps fail-fast (exit 1) instead of silently succeeding, preventing unsigned packages from reaching NuGet push. ADO Pipeline (esrp-publish.yml): - Add UseDotNet@2 task to Publish_NuGet stage so dotnet nuget push has a guaranteed SDK version on the Windows agent. Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1163) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(docs): fix OpenClaw sidecar demo and add limitations callout (#1164) The docker-compose example in openclaw-sidecar.md was illustrative only and did not work — it referenced a non-existent OpenClaw image and lacked healthchecks. Users were hitting this and getting confused. Changes: - Add working demo at demo/openclaw-governed/ with docker-compose.yaml that builds and runs the governance sidecar from source - Replace the inline docker-compose in the doc with a link to the demo plus a clearly-labeled reference template for custom deployments - Add prominent WARNING callout listing known limitations (no native OpenClaw integration, no published images, explicit API required) - Remove stale orphaned curl snippet after the docker-compose block - Add healthcheck to docker-compose governance-sidecar service - Fix OpenClaw image reference from ghcr.io/openclaw/openclaw:latest to a placeholder users must replace with their own image Co-authored-by: Copilot <[email protected]> * fix(ci): use PME tenant ID for ESRP cert signing The ESRP signing cert lives in the PME (Partner Managed Engineering) tenant (975f013f), not the Microsoft corporate tenant (72f988bf). Using the wrong tenant ID causes ESRP signing to fail when looking up the cert. Co-authored-by: Copilot <[email protected]> * docs: Add Scaling AI Agents article to COMMUNITY.md (#857) Co-authored-by: deepsearch <[email protected]> * Add runtime evidence mode to agt verify (#969) * Track agt verify evidence plan * Add runtime evidence mode to agt verify * Add runtime evidence verifier tests * Add CLI tests for agt verify evidence mode * Document evidence mode for compliance verification * Remove local implementation notes * Document agt verify evidence mode * Harden evidence path handling in verify --------- Co-authored-by: T. Smith <[email protected]> * docs: add Entra Agent ID bridge tutorial with R&R matrix and DID fix - Add Tutorial 31: Bridging AGT Identity with Microsoft Entra Agent ID - Detailed roles & responsibilities between AGT and Entra/Agent365 - Architecture diagram showing the identity bridge - Step-by-step: DID creation, Entra binding, AKS workload identity, token validation, lifecycle sync, access verification - Known gaps and limitations table - Platform independence note (AWS, GCP, Okta patterns) - Fix DID prefix in .NET MCP gateway tests (did:agentmesh → did:mesh for consistency with Python reference implementation and .NET SDK) - Update tutorials README with Enterprise Identity section Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]> * docs: address external critic gaps in limitations and threat model (#11) Add three new sections to LIMITATIONS.md addressing gaps identified in public criticism and external security analysis: - §10 Physical AI and Embodied Agent Governance: documents that AGT governs software agents not physical actuators, with mitigations - §11 Streaming Data and Real-Time Assurance: documents that AGT evaluates per-action not continuously over data streams - §12 DID Method Inconsistency Across SDKs: documents the did:mesh vs did:agentmesh split with migration plan for v4.0 Update THREAT_MODEL.md residual risks to reference all three new limitation sections. Co-authored-by: Copilot <[email protected]> * fix!: standardize DID method to did:agentmesh across all SDKs (#12) * fix!: standardize DID method to did:agentmesh across all SDKs BREAKING CHANGE: All agent DIDs now use the did:agentmesh: prefix. The legacy did:mesh: prefix used by Python and .NET has been migrated to match the did:agentmesh: convention already used by TypeScript, Rust, and Go SDKs. Changes: - Python: agent_id.py, delegation.py, entra.py, all integrations - .NET: AgentIdentity.cs, Jwk.cs, GovernanceKernel.cs, all tests - Docs: README, tutorials, identity docs, FAQ, compliance docs - Tests: all test fixtures updated across Python, .NET, TS, VSCode - Version bump: 3.1.0 → 3.2.0 (.NET, Python agent-mesh, TypeScript) Migration: replace did:mesh: with did:agentmesh: in your policies, identity registries, and agent configurations. Co-authored-by: Copilot <[email protected]> * docs: add Q11-Q13 to FAQ — AGT scope, Agent 365, and DLP comparison Adds three new customer Q&As: - Q11: Is AGT for Foundry agents or any agent type? (any) - Q12: Relationship between AGT and Agent 365 (different layers) - Q13: How is AGT different from DLP/communication compliance (content vs action governance) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> * fix(security): address all 14 open code scanning alerts (#13) * fix: address 6 Dependabot security vulnerabilities - python-multipart 0.0.22 → 0.0.26 (DoS via large preamble/epilogue) - pytest 8.4.1 → 9.0.3 (tmpdir handling vulnerability) - langchain-core 1.2.11 → 1.2.28 (SSRF, path traversal, f-string validation) - langchain-core >=0.2.0,<1.0 → >=1.2.28 in langchain-agentmesh pyproject.toml - tsup 8.0.0 → 8.5.1 (DOM clobbering vulnerability) - rand 0.8.5: dismissed #176 as inaccurate (vuln affects rand::rng() 0.9.x API only) Fixes Dependabot alerts: #177, #175, #166, #164, #157, #156 Dismissed: #176 (not applicable to rand 0.8.x) Co-authored-by: Copilot <[email protected]> * fix(security): address all 14 open code scanning alerts Scorecard HIGH: - publish-containers.yml: scope packages:write to job level (#316) Scorecard MEDIUM (pinned dependencies): - docs.yml: pin 4 GitHub Actions by SHA hash (#311-314) - docs.yml: use requirements.txt for pip install (#315) - agent-mesh Dockerfile: pin python:3.11-slim by SHA (#317,#318) - agent-os Dockerfile.sidecar: pin python:3.14-slim by SHA (#295,#296) - dashboard Dockerfile: pin python:3.12-slim by SHA (#291,#293) CodeQL: - test_time_decay.py: timedelta(days=365) -> 366 for leap safety (#289,#290) Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: kevinkaylie <[email protected]> Co-authored-by: Aymen Hmaidi <[email protected]> Co-authored-by: harshnair75567-cloud <[email protected]> Co-authored-by: Adamthereal <[email protected]> Co-authored-by: Jack Batzner <[email protected]> Co-authored-by: lawcontinue <[email protected]> Co-authored-by: deepsearch <[email protected]> Co-authored-by: ewmh <[email protected]> Co-authored-by: T. Smith <[email protected]>

github-actions Bot added documentation Improvements or additions to documentation tests agent-mesh agent-mesh package size/XL Extra large PR (500+ lines) labels Apr 12, 2026

github-actions Bot reviewed Apr 12, 2026

View reviewed changes

feat(typescript): add MCP security scanner and lifecycle management t…

fcbfd21

…o TS SDK Co-authored-by: Copilot <[email protected]>

imran-siddique force-pushed the feat/sdk-parity-ts branch from ecf299a to fcbfd21 Compare April 12, 2026 03:40

github-actions Bot reviewed Apr 12, 2026

View reviewed changes

imran-siddique merged commit 3f9e519 into microsoft:main Apr 12, 2026
73 of 81 checks passed

imran-siddique deleted the feat/sdk-parity-ts branch April 15, 2026 04:47

Conversation

imran-siddique commented Apr 12, 2026

Summary

MCP Security Scanner (mcp.ts)

Lifecycle Manager (lifecycle.ts)

Tests

Other

Uh oh!

github-actions Bot commented Apr 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Security Analysis of the Pull Request

1. Prompt Injection Defense Bypass

Finding: 🔴 CRITICAL

Attack Vector:

Recommendation:

2. Policy Engine Circumvention

Finding: 🟠 HIGH

Attack Vector:

Recommendation:

3. Trust Chain Weaknesses

Finding: 🔵 LOW

Recommendation:

4. Credential Exposure

Finding: 🔵 LOW

Recommendation:

5. Sandbox Escape

Finding: 🔵 LOW

Recommendation:

6. Deserialization Attacks

Finding: 🔵 LOW

Recommendation:

7. Race Conditions

Finding: 🟡 MEDIUM

Attack Vector:

Recommendation:

8. Supply Chain Risks

Finding: 🟠 HIGH

Attack Vector:

Recommendation:

Additional Observations

Summary of Findings and Recommendations

Final Recommendation: Request Changes

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

🤖 AI Agent: code-reviewer

Review Summary

🔴 CRITICAL: Security Issues

1. MCP Security Scanner: Unicode Homoglyph Detection

2. Lifecycle Manager: Lack of Authorization Checks

3. MCP Security Scanner: Risk Scoring

🟡 WARNING: Potential Breaking Changes

1. Lifecycle Manager API

2. Index.ts Barrel Exports

💡 Suggestions for Improvement

1. Thread Safety

2. Type Safety

3. Backward Compatibility

4. OWASP Agentic Top 10 Compliance

5. Documentation

Final Recommendations

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

🤖 AI Agent: code-reviewer

Pull Request Review: feat(typescript): add MCP security scanner and lifecycle management to TS SDK

🔴 CRITICAL: Security Issues

🟡 WARNING: Potential Breaking Changes

💡 Suggestions for Improvement

Summary of Actions

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

github-actions Bot commented Apr 12, 2026 •

edited

Loading