github-pr-review-fix

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

• Third-party content exposure detected (high risk: 0.95). The skill fetches PR review comments authored by other GitHub users via gh api repos/{owner}/{repo}/pulls/{number}/comments --paginate, then injects each comment_body (and thread replies) into sub-agent prompts for validation/fixing—i.e., outsider-authored free text enters the LLM context.