resolve-agent-reviews

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow instructs the agent to fetch and read PR review bot comments from the current GitHub PR (via "npx agent-reviews --bots-only --unanswered --expanded" and "--detail ") and then act on them (fix code, commit, and post replies), meaning it ingests untrusted, user-generated third-party content (PR/comments) that can materially change agent actions.