systematic-debugging

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

• Third-party content exposure detected (high risk: 0.90). The skill's Research phase (see SKILL.md "Research phase" / "Default research kinds") explicitly instructs running WebSearch and WebFetch via subagents to search error strings, open GitHub issues, and live docs—i.e., fetching and interpreting untrusted public web content that will influence the agent's analysis and next actions.