Xuehai Tang

RouteGuard is a novel detector that identifies skill poisoning in LLM agents by monitoring structured internal attention shifts, achieving high detection rates on critical skill-injection attacks.

The paper introduces SkillGuard-Robust, a novel framework for robust, cross-file security auditing of untrusted agent skills, achieving high accuracy on large-scale package evaluations.

This paper introduces a new benchmark to test Tool Description Poisoning (TDP) attacks on LLM agents, demonstrating that even advanced models like GPT-4o are highly vulnerable and that current defenses are often ineffective.