fix-ci

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and read CI job logs from GitHub Actions (e.g., via "gh run view --log-failed" and using user-provided run IDs/URLs), which are external, user-generated third-party content that the agent must interpret to decide fixes and actions.