review

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly fetches and reads public PRs/diffs (e.g., "gh pr view ...", "gh pr diff ..." in "Step 1: Fetch the Diff" and "PR mode" examples) and also performs external lookups (the ao lookup call in Step 0), so it ingests untrusted, user-generated third‑party content and acts on it (including producing/verdicts and optionally posting reviews), which could allow indirect prompt injection.