Skills
skills/inference-sh/skills/python-executor/Gen Agent Trust Hub

python-executor

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches setup instructions from a public GitHub repository belonging to the 'inference-sh' organization.
  • [REMOTE_CODE_EXECUTION]: This skill is intentionally designed to execute remote Python code in a sandboxed environment on the 'inference.sh' platform. This is the primary and documented function of the skill, and it provides appropriate warnings regarding its non-interactive and CPU-only nature.
  • [DATA_EXFILTRATION]: While the tool allows for general network access (e.g., via 'requests' or 'playwright'), this is consistent with its intended use cases for web scraping and API integration. No patterns of sensitive data harvesting or unauthorized exfiltration were found.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 01:11 PM
Security Audit — agent-trust-hub — python-executor