seedance-2-5-comic-drama-video

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text from the CLI --prompt (and optional --system) passed through cmd_chat()/client.chat_text() into the AI Hive POST /openapi/v1/chat/text, so an outsider can supply arbitrary text at generation time.