ai-model-gateway

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text from the caller’s variables.user_question (and any other user-supplied fields) into the LLM context via the render_prompt → safety_in → provider_call stages, which then pass that text to the model.