github-review-report

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches user-generated GitHub content via gh pr list and gh pr view (see run_gh_command and the extract_review_suggestions/AI prompt sections) and feeds original review bodies into AI analysis, so it clearly ingests untrusted third-party PR/review comments that could contain indirect prompt injection.