github-ci-fix

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

• Third-party content exposure detected (high risk: 0.85). The skill ingests outsider-authored free text from GitHub PR conversation content (comments/reviews/review thread bodies) via scripts/fetch_comments.py, which calls gh api graphql and includes body fields from comments, reviews, and reviewThreads into the agent’s LLM context.