Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems

arXiv:2605.11891v1 Announce Type: cross Abstract: Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both executable behavior and context-setting documentation, its deployment risk cannot be measured by single-shot audits or prompt-level red teams alone: a realistic attacker can use audit and runtime feedback to repeatedl