ci-watchdog

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses CI/PR data and logs from GitHub (e.g., "gh run view --log-failed" and "gh pr checks --json | python3 parse_failures.py" in SKILL.md and scripts/parse_failures.py), and it reads and acts on that user-generated third-party content to diagnose and apply fixes, which could allow indirect prompt injection.