fix-coderabbit-review

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

• Third-party content exposure detected (high risk: 0.90). This skill's exporter and resolver scripts (scripts/pr_review.py and scripts/resolve_pr_issues.py) call the GitHub REST/GraphQL APIs to fetch PR review comments, issue comments and review threads (user-generated content from GitHub PRs) and then parse and act on that content (generate issue files, decide resolution status, and run GraphQL mutations), so untrusted third-party comment text can directly influence the agent's workflow and actions.