research-methodology

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "search execution" tool routing explicitly instructs the agent to use WebSearch for live web results and WebFetch for reading known URLs (documentation pages, GitHub READMEs), so the agent will fetch and interpret untrusted public web content that can materially influence follow-up queries and actions.