loop-on-ci

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run "gh pr checks" and "gh run view --log-failed" to inspect PR-attached checks and GitHub Actions logs, which ingest and rely on untrusted, user-generated third-party content (PR checks/logs) to drive diagnosis and subsequent actions.