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

model-usage

Pass

Audited by Gen Agent Trust Hub on May 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script executes the codexbar CLI tool to retrieve usage data. The command construction is handled safely using a list of arguments, and input parameters like the provider are restricted to a predefined list of valid options.
  • [EXTERNAL_DOWNLOADS]: The skill includes an installation step for the codexbar tool via a Homebrew tap. This resource is a dependency provided by the author to support the skill's functionality.
  • [DATA_EXFILTRATION]: The skill reads local application logs to calculate costs. The data is processed locally within the script, with no evidence of network transmission or external data transfer.
Audit Metadata
Risk Level
SAFE
Analyzed
May 23, 2026, 08:31 PM
Security Audit — agent-trust-hub — model-usage