address-pr-feedback

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and parse user-generated GitHub PR content (e.g., gh api repos/{owner}/{repo}/issues//comments and multiple gh api graphql queries for review bodies and threads) and to act on that feedback (decide fixes, amend commits, reply, resolve threads), so untrusted third-party comments can materially influence actions and enable indirect prompt injection.