arXiv CS
open access
ActionGuard: Tool Call Authorization under Poisoned Skills
LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. However, malicious instructions inserted into an otherwise benign skill can cause a benign user request to trigger dangerous Tool Calls, including data exf
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- ActionGuard: Tool Call Authorization under Poisoned Skills#1144417
- When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents#1083383
- ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents#405550
- AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs#627618
- Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks#432464
Record · ID 1136768
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive