codexbar

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the codexbar command-line utility with various arguments such as usage, --provider, and --all-accounts to retrieve statistical data about AI service consumption.
  • [DATA_EXPOSURE]: The skill documentation describes the tool's mechanism for accessing local session data, such as browser cookies and OAuth caches, to authenticate with service providers without requiring the user to pass raw secrets via the command line.
  • [SAFE]: The analysis did not detect any signs of data exfiltration, malicious prompt injection, or obfuscated content. The skill's behavior is consistent with its stated purpose of reporting account usage statistics.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 12:11 PM
Security Audit — agent-trust-hub — codexbar