python-executor

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill primarily serves as documentation and a set of instructions for using the belt CLI to interact with a remote Python execution service (inference.sh).
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and documentation from raw.githubusercontent.com/inference-sh/ and inference.sh. These are well-known domains associated with the service provider and are documented neutrally as intended functionality for the skill's primary purpose.
  • [COMMAND_EXECUTION]: Example commands are provided for using the belt CLI (e.g., belt login, belt app run). These are standard usage examples for the documented service and do not execute dangerous commands locally or without user interaction.
  • [REMOTE_CODE_EXECUTION]: While the skill's purpose is to execute code, it specifically facilitates execution within a remote, sandboxed environment managed by a third-party service (inference.sh). There is no local code execution within the agent's environment itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:15 AM
Security Audit — agent-trust-hub — python-executor