coin

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

• Third-party content exposure detected (medium risk: 0.30). The Workflow script ingests outsider-authored free text via the user-supplied briefs (Phase 1 interview/brief file) and then feeds it into the Generate/Score/Lane prompts (A.briefs.truth, A.briefs.disguise, A.briefs.object, A.briefs.mining, and A.round2.deltas/co-creation) without needing to select a specific item first.