fix-pr-issues

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

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow explicitly ingests PR comments/review summaries, inline review comments/threads, failed GitHub Actions logs, and the BM_BOSSBOT_SUMMARY block from the PR body via gh pr view/PR data—these are outsider-authored free text from other contributors on GitHub.