AI Agent Design Skill

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows agents performing web retrieval (e.g., "tool_call: search_web" in the Trace, a "Web Search" sub-agent in Hierarchical Teams, and references to RAG/web retrieval), indicating the agent fetches and ingests open/public third‑party content which it reads and uses to influence decisions and tool actions.