arXiv cs.AIPaper
CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems
If you're deploying autonomous agents with modular skills, this is worth understanding before production. The core insight: composing skills is not the same as checking them in isolation. The paper defines the threat and introduces an attack benchmark, which means either integrating skill-composition checking into your orchestration layer, or accepting this class of vulnerability and monitoring for it.