seedance-2-5-ai-ad-video

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text provided via the required --prompt (and optional --system) arguments is sent directly into the runtime LLM request in client.chat_text(..., messages=...) / client.generate_video(..., prompt=...) without any first selecting a specific item from a monitored feed.