python-sdk

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill allows for standard Python environment management, including installing the inferencesh library and running SDK-based scripts.
  • [REMOTE_CODE_EXECUTION]: Documentation examples describe building agents with internal code execution and calculator tools; these are legitimate SDK capabilities for AI application development.
  • [DATA_EXFILTRATION]: The SDK facilitates standard data movement through file uploads to inference.sh storage and webhook notifications to external platforms like Slack.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:29 PM
Security Audit — agent-trust-hub — python-sdk