check

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

• Third-party content exposure detected (high risk: 0.90). The skill's Triage Mode explicitly pulls and acts on GitHub issues and PRs using commands like gh issue list / gh pr list and gh pr view, so it ingests untrusted, user-generated content from public GitHub that can directly influence actions (comments, merges, closes) and thus could enable indirect prompt injection.