text-to-video

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

• Third-party content exposure detected (medium risk: 0.30). The runtime generate workflow takes outsider-provided free text from the --prompt CLI argument and sends it in the OpenAPI request body to POST /openapi/v1/generation/video via client.generate_video(... prompt ...), making the prompt directly ingested by the hosted model.