Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design exposes two sequential control points to untrusted publishers: a static skill may steer an otherwise correct task onto an unnecessarily costly trajectory. Prior work studies selection manipulation, malicious skill…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
