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 execute method sends code strings to https://api.together.ai/tci/execute for processing.
  • Example usage includes installing packages via !pip install and executing complex data science workflows.
  • [EXTERNAL_DOWNLOADS]: The skill references and uses official SDKs (together for Python and together-ai for 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
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:06 PM