contracts

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow is drafting/reviewing user-supplied contract text (e.g., the operator’s counterparty draft or clauses) in “Review mode” without any requirement that the input be trusted first-party content, so outsider-authored free text is ingested directly from the operator/counterparty document.