j5ik2o-gh-pr-converge-loop

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required runtime workflow uses gh pr view/gh pr checks/gh run view --log-failed (and invokes follow-up skills) to read the text/metadata of a specific GitHub pull request’s checks and review threads, which an outsider can author via PR content and CI/log failures.