babysit

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text from GitHub PR review/root comment bodies is fetched at runtime via gh api .../pulls/comments/<id>, gh api .../issues/comments/<id>, and gh api .../pulls/<number>/reviews/<id> inside the required sub-skill triage-pr-comments, and that text is then used in the agent’s LLM context for analysis/reply.