knowledge-card-generator

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text directly via the prompt field (and related styles/constraints/design_config.brief_inputs[].content) submitted by the caller to the OneKey router https://agent.deepnlp.org/agent_router under api_id: "image_generator".