reviewing-code

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 public, user-generated GitHub PR content as part of its required workflow (see "If given a PR URL" with gh pr view PR_NUMBER and gh pr diff PR_NUMBER, and piping diffs into model prompts), so untrusted third-party content can directly influence reviews and tool use.