together-fine-tuning

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install official client libraries (together for Python and together-ai for Node.js) from public registries. These are legitimate, well-known dependencies required for interacting with the Together AI API.
  • [COMMAND_EXECUTION]: Included in the skill is a Python script (scripts/finetune_workflow.py) and various CLI examples that automate the fine-tuning lifecycle. These executions are necessary for the skill's primary purpose and do not perform unauthorized or hidden operations.
  • [SAFE]: Extensive analysis confirms the skill follows standard security practices for API integrations. It correctly uses environment variables for authentication, targets official API endpoints (api.together.xyz), and lacks any indicators of obfuscation, data exfiltration, or prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:06 PM