together-batch-inference
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts exclusively with official Together AI API endpoints (api.together.xyz) and documentation sites (together.ai). All network communication is aligned with the stated purpose of the skill.
- [SAFE]: Authentication is handled securely by recommending the use of environment variables for the TOGETHER_API_KEY, avoiding hardcoded secrets within the scripts or instructions.
- [SAFE]: Dependencies are restricted to official, reputable packages (together for Python and together-ai for TypeScript) from standard registries.
- [SAFE]: File operations are limited to preparing temporary JSONL input files and saving result outputs to the local directory, with no access to sensitive system paths or persistence mechanisms detected.
Audit Metadata