fix-ci

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and analyzes CI run logs and artifacts from GitHub using the GitHub CLI (e.g., gh run view --log-failed and gh run download in Steps 4–5), which are third-party/user-generated content the agent reads and interprets, exposing it to indirect prompt injection.