gh-pr-clean-loop

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches GitHub pull request review threads (user-generated content) via the "gh api graphql" THREAD_QUERY in scripts/pr_health.py and SKILL.md instructs the agent to read those thread bodies and triage/implement fixes and resolve threads, so untrusted third-party content can directly influence actions.