status-report

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow reads outsider-authored free text from a Git hosting service by paginating “every open PR” and then reading “inline review threads, top-level reviews, summaries, walkthroughs, suggestions, nitpicks, and reviewer status,” where PR reviews/threads are user-submitted content.