seedance-2-0
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as an instructional reference and technical manual for integrating video generation models. All code snippets provided are illustrative examples of tool usage.
- [CREDENTIALS_UNSAFE]: No hardcoded secrets were detected. The skill correctly identifies that sensitive API keys (FAL_KEY, HEYGEN_API_KEY, REPLICATE_API_TOKEN) should be managed via environment variables.
- [INDIRECT_PROMPT_INJECTION]: The skill provides structured prompt templates for video generation. While these templates process user-defined content, the skill serves as a formatting guide rather than a runtime execution engine for untrusted data. The documentation includes 'identity-anchor' phrases to help ensure consistency, which acts as a form of boundary management for the generation process.
- [EXTERNAL_DOWNLOADS]: The skill references several external URLs for official documentation and service pages (fal.ai, Replicate, Runway, ByteDance). These are well-known technology services directly related to the skill's primary function and do not pose a security risk.
Audit Metadata