Chaining Skills to Hijack LLM Agents
The research introduces APEX, a method to build adversarial skill chains that hijack LLM agents by using agent records to carry false claims of user approval across sequential skills. This chain successfully induces unwanted actions, such as file deletion, in many models. The study also evaluates a defense mechanism that checks skill outputs against the original request, showing it can reduce attack success but also negatively impact legitimate task performance.