"On the Security of Tool-Invocation Prompts for LLM-Based Agentic Systems: ..."

Yuchong Xie et al. (2025)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2509.05755

access: open

type: Informal or Other Publication

metadata version: 2025-10-12

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2509-05755
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2509-05755
Yuchong Xie, Mingyu Luo, Zesen Liu, Zhixiang Zhang, Kaikai Zhang, Yu Liu, Zongjie Li, Ping Chen, Shuai Wang, Dongdong She:
On the Security of Tool-Invocation Prompts for LLM-Based Agentic Systems: An Empirical Risk Assessment. CoRR abs/2509.05755 (2025)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.