seedance-2-0-video-reference-to-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 reaches the runtime LLM via the user-supplied --prompt (and optional --system) passed into AiHiveClient.chat_text(...)/generate_video(...) when the generate command runs, since the skill directly forwards these strings into the OpenAPI request body as prompt/messages.content.