handle-pr-feedback

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests reviewer comments and threads from pull requests (e.g., pull-request-tool.list_comments(pr_number, filter=unresolved) and pull-request-tool.fetch_reviews), which are untrusted, user-generated PR comments that the agent reads and classifies to drive actions.