code-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md Step 1: "For GitHub Pull Requests" — use gh pr view to read the title and description and gh pr diff to get code changes) requires the agent to fetch and interpret user-generated GitHub PR content, which is untrusted third-party data that can influence review decisions and actions.