gh-address-comments

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 user-generated GitHub review and issue comments via the gh API (see "Collect comments": gh api repos/{owner}/{repo}/pulls/{number}/comments and .../issues/{number}/comments) and then instructs the agent to summarize and act on those comments, so untrusted third-party content can directly influence its actions.