seedance-2-0
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates and code for processing user-supplied prompt strings to generate video content, which constitutes a surface for indirect prompt injection where malicious instructions could be hidden in processed data.
- Ingestion points: User input passed via the 'prompt' variable in the video_selector and seedance_video tool execution examples in SKILL.md.
- Boundary markers: The provided prompt templates do not include specific delimiters or 'ignore' instructions to isolate user-supplied content from the agent's instructions.
- Capability inventory: The skill environment is configured with Bash, Read, and Write permissions, which define the potential impact if a prompt injection were successfully executed.
- Sanitization: There are no explicit sanitization, escaping, or validation steps described for the input prompts before they are transmitted to the video generation endpoints.
Audit Metadata