fix-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches CI logs and PR review comments from GitHub using gh commands and GraphQL (e.g., "gh pr checks", "gh run view", and "gh api .../pulls/.../reviews" and reviewThreads) and feeds that untrusted, user-generated content (logs and reviewer comments) into the fixer subagent which must read/interpret it to decide code changes and actions.