social-media-posts-generator

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

• Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, the outsider-provided free text is the prompt (and related styles/constraints/brief_inputs[*].content) that the caller POSTs to Onekey Router https://agent.deepnlp.org/agent_router for the craftsman-agent/craftsman-agent image_generator API, and this text is ingested to generate the carousel contents.