seedream-5-lite-multi-reference-image

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) arguments that are passed directly into the AI Hive API request body (messages / prompt) for chat/text or generation/image.