seedance-2-0-image-reference-to-video

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text from the user-provided --prompt argument (and optional --system) and forwards it directly to the AI Hive /openapi/v1/chat/text endpoint via cmd_chat → client.chat_text(...), making it an indirect prompt-injection surface.