address-review

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 user-generated PR review comments, top-level reviews, general issue comments, and CI check outputs from GitHub via gh api / gh pr commands (e.g., repos/{owner}/{repo}/pulls/{number}/comments, /reviews, issues/{number}/comments, gh pr checks) and is required to read and act on that content to triage and apply fixes, so untrusted third‑party text can materially influence its actions.