affinage

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

• Third-party content exposure detected (high risk: 0.95). /affinage fetches outsider-authored free text from the PR via gh api repos/<owner>/<repo>/pulls/<pr>/comments (inline review comments) and gh api repos/<owner>/<repo>/pulls/<pr>/reviews (review bodies), then includes those comment/review texts in the agent’s grading context and report.