Skills
skills/thinkfleetai/thinkfleet-engine/claude-code-usage/Gen Agent Trust Hub

claude-code-usage

Warn

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill documentation indicates it retrieves sensitive OAuth tokens from the macOS Keychain or Linux secret-tool to authenticate with the Anthropic API.
  • [COMMAND_EXECUTION]: The skill implements automated monitoring through self-scheduling tasks that dynamically create and manage cron jobs on the host system.
  • [COMMAND_EXECUTION]: The skill relies on the execution of local shell scripts and suggests the use of sudo for installing required system packages like libsecret-tools.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:14 AM