loop-on-ci

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required workflow ingests GitHub PR-attached check metadata via gh pr checks/gh pr checks --watch --fail-fast (and may follow failing-check GHA logs via gh run view --log-failed), and these check details can be influenced by outsider-authored PR content.