resolve-pr-feedback

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests GitHub PR review threads, PR comments, and review bodies via scripts/get-pr-comments and get-thread-for-comment (using the gh API) and passes the full user-generated comment text to resolver agents that read and act on it, so untrusted third-party content can influence agent decisions and actions.