resolve-reviews

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly runs npx agent-reviews --unanswered --expanded (Step 1) to fetch full GitHub PR review comments and then reads/interprets those human- and bot-written comment bodies (Step 3) to decide fixes, commits, and replies, so untrusted user-generated PR content can directly influence agent actions.