pr-review-loop

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 path scripts/pr_loop.py collect reads outsider-authored free text from GitHub PR comment bodies and review bodies across reviewThreads, pulls/{pr}/reviews, and issues/{pr}/comments (and then fences/scans them), so an outsider can inject via posted PR review/comment content.