model-usage

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/model_usage.py executes the codexbar command using subprocess.check_output. This execution is safe as the command arguments are hardcoded or constrained to specific allowed values ('codex' or 'claude') via argparse.
  • [EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of codexbar using Homebrew. This is a standard package management operation on macOS for the intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 04:10 PM
Security Audit — agent-trust-hub — model-usage