monitoring-ci

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls out and runs gh commands (see ci-monitor.py and SKILL.md) to fetch and display GitHub Actions run data and failed job logs via "gh run view --log-failed", which are untrusted, user-generated third‑party contents that the agent reads and uses to decide/report CI status.