pr-monitoring-loop

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

• Third-party content exposure detected (high risk: 0.95). The required runtime path is scripts/check-pr-state.py → fetch_all() → issue_comments()/review_comments()/review_threads() which pulls outsider-authored PR comment/review/thread body text from GitHub and includes it in the LLM-visible focused JSON (format_focused() includes comments.*.body and threadDetails.*.comments[].body).