babysit-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and scripts/monitor.sh explicitly instruct the agent to run gh pr checks / gh run view to read GitHub Actions logs and PR details (untrusted, user-generated content) and to base diagnoses, fixes, and merge decisions on that content, so third-party CI/PR output can materially influence actions.