check-reviewgate

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

• Third-party content exposure detected (high risk: 0.85). Runtime path: the workflow uses gh api to fetch PR issue/pull request comments (repos/{owner}/{repo}/issues/$PR_NUMBER/comments and repos/{owner}/{repo}/pulls/$PR_NUMBER/comments) and then parses their body text into the agent context as fallback review summary and inline finding comments—this is outsider-authored free text.