Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents
Researchers present TrustProbe, a framework for detecting vulnerabilities in skill-based LLM agents. They analyze 11 open-source agents and find 104 taint-style vulnerabilities, 25.1% of which are exercised in real-world skill-agent trials, demonstrating a systematic trust failure in skill-based LLM agents.
Save an API key to vote.