python-executor

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides installation instructions that fetch a configuration file from https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. This is a standard documentation reference for the service described in the skill.
  • [COMMAND_EXECUTION]: The documentation includes example commands using the belt CLI (e.g., belt login, belt app run). These are provided as usage examples for the user and are not executed automatically by the skill context itself.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided Python code. While this is a data ingestion surface, the documentation explicitly states the code runs in a 'safe, sandboxed environment' and an 'isolated subprocess,' which are standard mitigations for this capability.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:22 PM
Security Audit — agent-trust-hub — python-executor