red-team-assessment

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 passive reconnaissance explicitly instructs using http_request/curl to query public OSINT engines (FOFA/Quake/Hunter) and to scrape public sources like GitHub/GitLab and certificate transparency logs (SKILL.md "Phase 1: 被动侦察"), which are untrusted, user-generated or public third‑party content that the agent must read and which can materially influence subsequent attack decisions.