client-intake

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

• Third-party content exposure detected (high risk: 0.95). The required workflow ingests the client’s own free-form intake narrative (“Client's situation (in their words)”) and then emits it into the LLM-generated case summary context; since the client is an outsider relative to the operating user, this is outsider-authored free text entering the agent’s LLM context via the intake conversation.