vp-pr-comment-resolver

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly fetches and ingests GitHub PR review threads and PR discussion comments using gh api graphql (Phase 1 / "Fetch Comments") and then reads and acts on those user-generated comment bodies to decide fixes, commits, replies, and whether to resolve threads, which exposes the agent to untrusted third-party content.