seedance-motion
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied action briefs to generate structured motion prompts. While the instructions are benign, this workflow inherently creates a surface for indirect prompt injection where instructions embedded within a user's brief might attempt to influence the agent's behavior.
- Ingestion points: User-provided briefs for body action, choreography, physics, or motion-reference mapping.
- Boundary markers: None are explicitly defined in the prompt generation instructions.
- Capability inventory: The skill generates prompt text, timing patterns, and repaired prompt language for video generation models.
- Sanitization: There are no explicit instructions to sanitize or escape the content of the user's motion brief before it is processed into prompt language.
Audit Metadata