skills/steipete/clawdis/model-usage/Gen Agent Trust Hub

model-usage

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The Python script scripts/model_usage.py utilizes subprocess.check_output to execute the codexbar CLI tool. This execution is performed using a list-based argument structure with inputs sanitized through argparse choices, which effectively mitigates command injection risks.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the codexbar utility via a Homebrew tap (steipete/tap/codexbar). This external dependency is owned by the same author as the skill and is required for its documented functionality.\n- [SAFE]: The skill processes local data such as cost logs and usage statistics (e.g., from ~/.codex or ~/.config/claude). No unauthorized network communication or data exfiltration patterns were identified during the analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 11:05 PM