seedance-2-0
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a comprehensive manual for integrating the ByteDance Seedance 2.0 model via various APIs (fal.ai, Replicate, Runway, etc.).
- [SAFE]: YAML frontmatter correctly scopes the skill using
allowed-tools(Bash, Read, Write) and identifies required environment variables for API authentication without hardcoding any secrets. - [SAFE]: Network references are directed towards official documentation and established AI provider domains (fal.ai, replicate.com, runwayml.com, etc.), which are well-known services.
- [SAFE]: The 'Prompt structure' section provides legitimate creative engineering techniques (temporal markers, shot-structure declarations, and identity-anchor phrases) rather than prompt injection or bypass attempts.
- [SAFE]: No obfuscation, persistence mechanisms, or dynamic code execution patterns were found in the instructions or code examples provided.
Audit Metadata