address-pr-comments

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 reads user-generated GitHub review comments via the gh API (see SKILL.md Step 2 and references/gh-api-reference.md: "gh api repos/{owner}/{repo}/pulls/{pr_number}/comments --paginate"), and those untrusted comment bodies are used to decide code changes and draft/post threaded replies, so third‑party content can directly influence agent actions.