seedance-2-prompt
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's implementation follows security best practices for API-based media generation and file handling.
- [COMMAND_EXECUTION]: The entrypoint executes a controlled Python script. The script uses standard argument parsing and does not utilize unsafe execution functions like eval or shell=True subprocess calls with user input.
- [EXTERNAL_DOWNLOADS]: Network operations are performed against well-known AI service providers (OpenRouter, Volcengine, and BytePlus). The script includes host-gating logic to ensure Authorization headers are only sent to the authorized service (openrouter.ai) and stripped for third-party object storage URLs.
- [CREDENTIALS_UNSAFE]: Sensitive API keys are managed through environment variables or local configuration files (opensquilla.toml) rather than being hardcoded in the source code.
Audit Metadata