setup-enformer-remote-tool

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads a Python wheel from connect.aiscientist.tools. This is documented as an official platform component for the ToolUniverse Connect relay service. The download includes a SHA-256 hash pin (3fad5eee5ecf7887a693d93ccd1aa112dc0955617a885d1fc3daded0030f9ae0) to ensure file integrity.
  • [COMMAND_EXECUTION]: The skill provides various shell commands for environment setup, package installation, and server execution. These include pip install, venv creation, and executing ToolUniverse CLI commands (tu remote login, tu remote share). These are standard operations for deploying this type of service.
  • [CREDENTIALS_UNSAFE]: The instructions explicitly emphasize safe credential handling, advising users to keep secrets in protected environment files or .env files and to avoid passing tokens as command-line arguments. It describes using a device-code authorization flow which prevents the need for manual key copying.
  • [REMOTE_CODE_EXECUTION]: The skill demonstrates how to interact with the deployed model via a local MCP (Model Context Protocol) client using Python scripts. These scripts connect to the loopback interface (127.0.0.1) and are used for validation purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 08:19 AM
Security Audit — agent-trust-hub — setup-enformer-remote-tool