seedance-motion

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow ("1. The Recommended Workflow: Intent + @Video Reference" Step 1) explicitly instructs the user to find and upload a real-world reference video (uploaded as @Video1) from public sources and tells the model to reference that video, so untrusted third-party content is ingested and can directly influence the agent's actions.