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

model-usage

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/model_usage.py utilizes the subprocess.check_output method to execute the codexbar CLI utility. The command parameters are sanitized through an argument parser with fixed choices, mitigating the risk of command injection.
  • [DATA_EXFILTRATION]: The skill identifies and reads from sensitive local directories containing session history, specifically ~/.codex/sessions/ and directories related to Claude projects (e.g., ~/.config/claude/projects/). This access is fundamental to the skill's primary purpose of cost analysis but involves handling sensitive user information.
  • [EXTERNAL_DOWNLOADS]: The skill's configuration specifies the installation of a binary dependency (codexbar) from a third-party Homebrew tap (steipete/tap/codexbar). This repository is owned by the skill's author and is required for the tool's core functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 03:41 AM