resolve-pr-feedback

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text from GitHub review threads/comments/bodies is fetched at runtime via scripts/get-pr-comments (GraphQL body fields) and then passed into the LLM context for judging/fixing/reply composition in the required workflow (e.g., step 3 gate and fixer dispatch in references/full-mode.md / references/agents/pr-comment-resolver.md).