skills/glebis/claude-skills/setup/Gen Agent Trust Hub

setup

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches required Python packages including 'natasha', 'scrubadub', and 'phonenumbers' from the official Python Package Index (PyPI).
  • [EXTERNAL_DOWNLOADS]: Downloads the 'qwen2.5:3b' model from the Ollama model registry using the 'ollama pull' command.
  • [COMMAND_EXECUTION]: Executes 'pip install' and 'ollama pull' via the subprocess module to set up the local environment. The execution uses safe argument lists rather than shell strings.
  • [DATA_EXFILTRATION]: Probes the local Ollama API endpoint (localhost:11434) to verify model readiness. No sensitive data is transmitted to external or untrusted domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:20 PM
Security Audit — agent-trust-hub — setup