logo-designer-generator

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow sends user-supplied free text fields (notably data.prompt and design_config.brief_inputs[].content) directly as the prompt/layer text for the craftsman-agent/craftsman-agent image_generator API via https://agent.deepnlp.org/agent_router, so outsiders can inject arbitrary text through the POST request body.