superreview-setup

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

• Third-party content exposure detected (medium risk: 0.30). The workflow’s required runtime path ingests outsider-authored free text from the user’s {USER_REQUEST} chat prompt into the emitted intent-guard agent as “the request, VERBATIM (tier 5, and tier 1 when no external source exists),” and that agent is always spawned at both QUICK and EXTENDED depths.