review-comments

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

• Third-party content exposure detected (medium risk: 0.30). In the required workflow, the agent reads outsider-authored free text from GitHub PR reviewThreads/comments via the gh api graphql query in step 3 and also drafts comments based on PR diff/content it fetches in step 5 (gh pr view and git fetch origin refs/pull/...).