together-code-interpreter
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to facilitate the execution of arbitrary Python code and shell commands (via
!) within a remote, sandboxed environment provided by Together AI. - The
executemethod sends code strings tohttps://api.together.ai/tci/executefor processing. - Example usage includes installing packages via
!pip installand executing complex data science workflows. - [EXTERNAL_DOWNLOADS]: The skill references and uses official SDKs (
togetherfor Python andtogether-aifor Node.js) and connects to a well-known service endpoint (api.together.ai). These references are documented and align with the skill's stated purpose. - [CREDENTIALS_UNSAFE]: Security best practices are followed for credential handling; the skill and its accompanying scripts use environment variables (e.g.,
TOGETHER_API_KEY) rather than hardcoded secrets.
Audit Metadata