skills/nousresearch/hermes-agent/grok/Gen Agent Trust Hub

grok

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The documentation includes a command to download and execute an installation script from the official x.ai domain. This is provided as a standard installation method for the CLI tool.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the official '@xai-official/grok' package from the public npm registry as the preferred installation path.
  • [COMMAND_EXECUTION]: The skill uses shell commands through the terminal tool to manage the Grok CLI, including headless execution, session persistence, and interactive sessions via tmux.
  • [CREDENTIALS_UNSAFE]: The instructions involve checking for local authentication state in the '~/.grok/auth.json' file and support the use of the 'XAI_API_KEY' environment variable for service access.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:31 AM
Security Audit — agent-trust-hub — grok