20-client-intake-brief-global

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is an “input gate” where the operating client fills in the intake template (Sections A–K) and the agent ingests that returned free-text into the LLM context; this is outsider-authored content because it comes from the client/other party rather than the operating user’s own authored prompts/files.