seedance

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 via the user-supplied --prompt (and optional --system) passed directly to the external AI Hive API in cmd_chat()/client.chat_text() (and cmd_video()/client.generate_video() uses args.prompt), without any need to first select an item from a monitored queue/feed.