feat(dotnet): add MCP security namespace — completes cross-language MCP parity by imran-siddique · Pull Request #1021 · microsoft/agent-governance-toolkit

imran-siddique · 2026-04-15T04:16:58Z

Summary

Adds the \AgentGovernance.Mcp\ namespace to the .NET SDK, closing the last gap in cross-language MCP security parity. All 5 languages (Python, TypeScript, .NET, Rust, Go) now have MCP security coverage.

New classes in \AgentGovernance.Mcp\

Class	Purpose
\McpSecurityScanner\	Tool metadata scanning: poisoning, typosquatting, hidden instructions, rug pull, schema abuse, cross-server attack, description injection
\McpCredentialRedactor\	Regex-based redaction of API keys, bearer tokens, connection strings, secret assignments
\McpResponseSanitizer\	Response scanning for prompt injection tags, imperative phrasing, credential leakage, exfiltration URLs
\McpGateway\	Policy enforcement pipeline: deny/allow lists, payload sanitization, rate limiting, human approval gates

Details

Tests: 46 new xUnit tests, all 513 total pass
Docs: Updated \SDK-FEATURE-MATRIX.md\ — .NET MCP Security flipped from \—\ to checkmark
Design: Follows existing .NET SDK conventions (sealed classes, XML doc comments, no new NuGet deps). Thread-safe. Reuses existing \RateLimiter. Matches TS scanner threat categories + Rust gateway/redaction/sanitization surface.

…CP 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]>

github-actions · 2026-04-15T05:03:24Z

🤖 AI Agent: breaking-change-detector — Summary

🔍 API Compatibility Report

Summary

This pull request introduces a new namespace AgentGovernance.Mcp to the .NET SDK, adding several new classes and methods to support MCP security features. The changes are additive and do not modify or remove any existing APIs. Therefore, there are no breaking changes in this update.

Findings

Severity	Package	Change	Impact
🔵	agent-governance-dotnet	Added `AgentGovernance.Mcp` namespace with new classes (`McpSecurityScanner`, `McpCredentialRedactor`, `McpResponseSanitizer`, `McpGateway`)	New functionality, no impact on existing code

Migration Guide

No migration is required as there are no breaking changes. Downstream users can adopt the new AgentGovernance.Mcp namespace and utilize its features without modifying their existing code.

Notes

The new classes (McpSecurityScanner, McpCredentialRedactor, McpResponseSanitizer, McpGateway) should be documented thoroughly to ensure developers understand their usage and capabilities.
Ensure that the new functionality aligns with the conventions and patterns of the existing .NET SDK for consistency.

✅ No breaking changes detected.

github-actions · 2026-04-15T05:03:27Z

🤖 AI Agent: docs-sync-checker — Issues Found

📝 Documentation Sync Report

Issues Found

❌ McpCredentialRedactor.Redact() in packages/agent-governance-dotnet/src/AgentGovernance/Mcp/McpCredentialRedactor.cs — missing detailed docstring for parameters and return values.
❌ McpGateway.ProcessRequest() in packages/agent-governance-dotnet/src/AgentGovernance/Mcp/McpGateway.cs — missing detailed docstring for parameters and return values.
❌ McpResponseSanitizer.ScanText() in packages/agent-governance-dotnet/src/AgentGovernance/Mcp/McpResponseSanitizer.cs — missing docstring.
⚠️ packages/agent-governance-dotnet/README.md — no mention of the new Mcp namespace or its classes and functionality.
⚠️ CHANGELOG.md — no entry for the addition of the new Mcp namespace and its classes.

Suggestions

💡 Add detailed docstrings for the following methods:
- McpCredentialRedactor.Redact(input: str) -> RedactionResult: Explain the purpose of the method, the input parameter, and the structure of the returned RedactionResult.
- McpGateway.ProcessRequest(request: McpGatewayRequest) -> McpGatewayDecision: Describe the request parameter and the McpGatewayDecision return type, including its fields.
- McpResponseSanitizer.ScanText(input: str) -> McpSanitizedResponse: Provide a description of the method, the input parameter, and the McpSanitizedResponse return type.
💡 Update packages/agent-governance-dotnet/README.md to include a new section detailing the Mcp namespace, its purpose, and how to use the new classes (McpSecurityScanner, McpCredentialRedactor, McpResponseSanitizer, McpGateway).
💡 Add an entry to CHANGELOG.md summarizing the addition of the Mcp namespace and its new classes to the .NET SDK, emphasizing the completion of cross-language MCP security parity.

Additional Notes

The new public APIs include type annotations, which is good.
The examples directory (examples/) does not appear to exist for the .NET SDK. If examples are maintained elsewhere, ensure they are updated to include usage of the new Mcp namespace.
The docs/SDK-FEATURE-MATRIX.md and docs/compliance/soc2-mapping.md have been updated to reflect the new functionality, which is good.

Please address the issues and suggestions above to ensure documentation is fully in sync with the new changes.

github-actions · 2026-04-15T05:03:33Z

🤖 AI Agent: security-scanner — Security Review of Pull Request: `feat(dotnet): add MCP security namespace`

Security Review of Pull Request: `feat(dotnet): add MCP security namespace`

This pull request introduces the AgentGovernance.Mcp namespace to the .NET SDK, implementing critical security features such as metadata scanning, credential redaction, response sanitization, and policy enforcement. Below is a detailed security analysis of the changes:

Findings

1. Prompt Injection Defense Bypass

Issue: The McpResponseSanitizer uses regex patterns to detect and sanitize prompt injection tags and imperative phrasing. Regex-based detection is inherently limited and can be bypassed by obfuscation, encoding, or paraphrasing.
Attack Vector: An attacker could craft payloads that evade the regex patterns, such as using Unicode homoglyphs, splitting keywords across multiple lines, or using non-English languages.
Severity: 🔴 CRITICAL
Recommendation:
- Implement semantic analysis for prompt injection detection, leveraging NLP techniques to identify intent rather than relying solely on regex.
- Incorporate multilingual support to handle non-English inputs.
- Use a combination of static and dynamic analysis to detect obfuscated patterns.

2. Policy Engine Circumvention

Issue: The McpGateway enforces deny/allow lists, payload sanitization, and rate limiting. However, the BlockOnSuspiciousPayload flag defaults to true but can be disabled. If disabled, suspicious payloads are allowed to proceed.
Attack Vector: A misconfigured or malicious deployment could disable BlockOnSuspiciousPayload, allowing malicious payloads to bypass sanitization and enforcement.
Severity: 🟠 HIGH
Recommendation:
- Make BlockOnSuspiciousPayload non-configurable or enforce it as true by default in critical environments.
- Log and alert on any attempts to disable or modify this setting.

3. Trust Chain Weaknesses

Issue: No explicit SPIFFE/SVID validation or certificate pinning mechanisms are mentioned in the McpGateway or related classes.
Attack Vector: An attacker could exploit a lack of trust chain validation to impersonate agents or inject malicious payloads.
Severity: 🟠 HIGH
Recommendation:
- Integrate SPIFFE/SVID validation to ensure agent identity and trustworthiness.
- Implement certificate pinning to prevent man-in-the-middle (MITM) attacks.

4. Credential Exposure

Issue: The McpCredentialRedactor uses regex patterns to redact credentials. While it covers common patterns (e.g., API keys, bearer tokens, connection strings), it may miss less common or obfuscated credential formats.
Attack Vector: Credentials not matching the predefined regex patterns could be logged or exposed in error messages.
Severity: 🟡 MEDIUM
Recommendation:
- Expand the regex patterns to include additional credential formats.
- Use a heuristic-based approach to detect potential credentials (e.g., entropy analysis).
- Ensure all logs and error messages pass through the redactor before being persisted.

5. Sandbox Escape

Issue: No evidence of sandboxing or process isolation mechanisms for executing tools or handling payloads.
Attack Vector: Malicious payloads could exploit the lack of isolation to execute arbitrary code or access sensitive resources.
Severity: 🔴 CRITICAL
Recommendation:
- Enforce strict sandboxing for tool execution, such as using containerized environments or restricted process sandboxes.
- Limit the permissions and resources available to the sandboxed environment.

6. Deserialization Attacks

Issue: The McpGatewayRequest.Payload field accepts serialized JSON as input. There is no indication of validation or sanitization of deserialized data.
Attack Vector: An attacker could craft malicious JSON payloads to exploit deserialization vulnerabilities.
Severity: 🟠 HIGH
Recommendation:
- Validate and sanitize all deserialized data before processing.
- Use a secure JSON deserialization library that enforces strict schema validation.

7. Race Conditions

Issue: The McpGateway relies on a rate limiter to enforce per-agent throttling. However, there is no indication of locking or atomic operations to prevent race conditions in concurrent requests.
Attack Vector: An attacker could exploit a time-of-check-to-time-of-use (TOCTOU) race condition to bypass rate limiting.
Severity: 🟠 HIGH
Recommendation:
- Use atomic operations or distributed locks to ensure thread-safe rate limiting.
- Test the rate limiter under high-concurrency scenarios to identify potential race conditions.

8. Supply Chain Risks

Issue: The PR does not introduce new dependencies, but existing dependencies are not explicitly validated for supply chain risks.
Attack Vector: Dependency confusion or typosquatting attacks could compromise the library.
Severity: 🟡 MEDIUM
Recommendation:
- Use a dependency scanning tool to identify and mitigate supply chain risks.
- Pin dependency versions and verify their integrity using checksums or signatures.

Summary of Findings

Finding	Severity	Recommendation Summary
Prompt Injection Defense Bypass	🔴 CRITICAL	Use semantic analysis, multilingual support, and dynamic analysis for robust detection.
Policy Engine Circumvention	🟠 HIGH	Enforce `BlockOnSuspiciousPayload` as non-configurable or always `true`.
Trust Chain Weaknesses	🟠 HIGH	Add SPIFFE/SVID validation and certificate pinning.
Credential Exposure	🟡 MEDIUM	Expand regex patterns, use heuristics, and sanitize logs and error messages.
Sandbox Escape	🔴 CRITICAL	Implement strict sandboxing and resource isolation for tool execution.
Deserialization Attacks	🟠 HIGH	Validate and sanitize deserialized data; enforce strict schema validation.
Race Conditions	🟠 HIGH	Use atomic operations or locks for rate limiting.
Supply Chain Risks	🟡 MEDIUM	Perform dependency scanning and enforce version pinning with integrity checks.

Final Recommendation

This pull request introduces critical security features but also presents significant risks, particularly in the areas of prompt injection defense, sandboxing, and deserialization. Addressing these issues is essential before merging to ensure the robustness of the MCP security layer.

github-actions

🤖 AI Agent: code-reviewer

Pull Request Review: feat(dotnet): add MCP security namespace — completes cross-language MCP parity

This pull request introduces the AgentGovernance.Mcp namespace to the .NET SDK, achieving cross-language parity for MCP security features. The new namespace includes classes for credential redaction, response sanitization, and policy enforcement. Below is a detailed review of the changes with a focus on security, correctness, and compliance.

🔴 CRITICAL Issues

Regex Timeout and DoS Risk in McpCredentialRedactor and McpResponseSanitizer
- The regex patterns in McpCredentialRedactor and McpResponseSanitizer use a timeout of 200ms (RegexTimeout). While this is a good safeguard, the complexity of the regex patterns (e.g., (?i)(?:api[_\-]?key|x-api-key)\s*[:=]\s*[""']?[a-z0-9_\-]{8,}[""']?) could still lead to catastrophic backtracking under certain inputs, especially if an attacker crafts payloads with malicious intent.
- Recommendation: Use simpler, non-backtracking regex patterns or pre-compile the regex with the RegexOptions.NonBacktracking flag (available in .NET 7+). Additionally, consider adding input length checks to reject excessively large payloads before applying regex.
Credential Redaction Incompleteness
- The McpCredentialRedactor relies solely on regex patterns to detect and redact credentials. This approach is prone to false negatives, especially for non-standard credential formats or obfuscated secrets.
- Recommendation: Augment regex-based detection with heuristic or ML-based methods to identify non-standard credential patterns. Additionally, log any unredacted payloads for further analysis (ensure logs are secure and do not inadvertently leak sensitive data).
Insufficient Payload Sanitization in McpResponseSanitizer
- The McpResponseSanitizer focuses on specific threat types (e.g., prompt injection tags, imperative phrasing). However, it lacks semantic analysis for multilingual or obfuscated threats, which could bypass regex-based detection.
- Recommendation: Incorporate semantic analysis (e.g., NLP models) to detect threats beyond regex patterns. For example, use a pre-trained transformer model to identify paraphrased prompt injection attempts.
Policy Enforcement Gaps in McpGateway
- The McpGateway enforces deny/allow lists, payload sanitization, rate limiting, and human approval. However, the BlockOnSuspiciousPayload flag defaults to true, which may not be sufficient for high-security environments.
- Recommendation: Introduce a stricter mode where any suspicious payload findings automatically block the request, regardless of the flag's value. Additionally, log all denied requests for audit purposes.

🟡 WARNING Issues

Breaking Changes in Public API
- The addition of the AgentGovernance.Mcp namespace introduces new public classes and methods. While this is an additive change, any future modifications to these APIs could break backward compatibility.
- Recommendation: Clearly document the new APIs as "Experimental" or "Beta" if they are subject to change. Use semantic versioning to signal breaking changes in future releases.
Rate Limiting Behavior in McpGateway
- The McpGateway uses a rate limiter to throttle requests. However, the RetryAfterSeconds value is hardcoded to 60 seconds, which may not align with the actual rate-limiting configuration.
- Recommendation: Dynamically calculate RetryAfterSeconds based on the rate limiter's state to provide accurate feedback to clients.

💡 Suggestions for Improvement

Thread Safety Documentation
- The new classes (McpCredentialRedactor, McpResponseSanitizer, McpGateway) are described as thread-safe, but the documentation does not specify how thread safety is achieved (e.g., immutability, synchronization).
- Recommendation: Add explicit comments or annotations to clarify the thread safety guarantees and any limitations.
Enhanced Logging for Debugging
- The McpGateway and McpResponseSanitizer do not log detailed information about findings or decisions. This could hinder debugging and auditing efforts.
- Recommendation: Implement structured logging for key events (e.g., payload sanitization findings, denied requests) with configurable log levels to balance security and performance.
SOC 2 Compliance Mapping
- The updated SOC 2 compliance mapping highlights several gaps (e.g., detection modules not wired to enforcement, no consent management). While some issues are marked as resolved, others remain open.
- Recommendation: Prioritize resolving high-impact gaps, such as wiring detection modules into the enforcement lifecycle and adding consent management features.
Unit Test Coverage
- The pull request mentions 46 new xUnit tests, but it does not specify the coverage for edge cases (e.g., malformed payloads, extreme rate-limiting scenarios).
- Recommendation: Ensure comprehensive test coverage for edge cases, including malformed inputs, large payloads, and high-concurrency scenarios.

Summary of Recommendations

Category	Priority	Recommendation
🔴 Security	High	Simplify regex patterns to avoid catastrophic backtracking.
🔴 Security	High	Augment regex-based redaction with heuristic or ML-based methods.
🔴 Security	High	Incorporate semantic analysis for multilingual or obfuscated threats.
🔴 Security	High	Introduce stricter policy enforcement in `McpGateway`.
🟡 Breaking Change Risk	Medium	Mark new APIs as "Experimental" and use semantic versioning for future changes.
🟡 Usability	Medium	Dynamically calculate `RetryAfterSeconds` in `McpGateway`.
💡 Documentation	Low	Clarify thread safety guarantees in class documentation.
💡 Debugging	Low	Add structured logging for key events in `McpGateway` and `McpResponseSanitizer`.
💡 Compliance	Medium	Address SOC 2 compliance gaps (e.g., consent management, enforcement wiring).
💡 Testing	Medium	Ensure comprehensive test coverage for edge cases and high-concurrency scenarios.

Final Assessment

The addition of the AgentGovernance.Mcp namespace is a significant step toward cross-language MCP security parity. However, the reliance on regex-based detection and the lack of semantic analysis introduce potential security risks. Addressing these issues should be a priority to ensure robust and reliable security features. Additionally, the team should focus on improving documentation, logging, and compliance to enhance the overall quality and maintainability of the codebase.

* 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]>

imran-siddique merged commit 0ed4055 into microsoft:main Apr 15, 2026
25 of 27 checks passed

github-actions Bot added documentation Improvements or additions to documentation tests size/XL Extra large PR (500+ lines) labels Apr 15, 2026

github-actions Bot reviewed Apr 15, 2026

View reviewed changes

Conversation

imran-siddique commented Apr 15, 2026

Summary

New classes in \AgentGovernance.Mcp\

Details

Uh oh!

Uh oh!

github-actions Bot commented Apr 15, 2026

🔍 API Compatibility Report

Summary

Findings

Migration Guide

Notes

Uh oh!

github-actions Bot commented Apr 15, 2026

📝 Documentation Sync Report

Issues Found

Suggestions

Additional Notes

Uh oh!

github-actions Bot commented Apr 15, 2026

Security Review of Pull Request: feat(dotnet): add MCP security namespace

Findings

1. Prompt Injection Defense Bypass

2. Policy Engine Circumvention

3. Trust Chain Weaknesses

4. Credential Exposure

5. Sandbox Escape

6. Deserialization Attacks

7. Race Conditions

8. Supply Chain Risks

Summary of Findings

Final Recommendation

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

🤖 AI Agent: code-reviewer

Pull Request Review: feat(dotnet): add MCP security namespace — completes cross-language MCP parity

🔴 CRITICAL Issues

🟡 WARNING Issues

💡 Suggestions for Improvement

Summary of Recommendations

Final Assessment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Security Review of Pull Request: `feat(dotnet): add MCP security namespace`