grok-cli-runtime

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides troubleshooting steps for managing the grok binary's authentication and quota states. It correctly advises treating authentication files as opaque objects and explicitly warns against extracting or documenting their fields.
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill mentions sensitive file paths such as ~/.grok/auth.json and environment variables like XAI_API_KEY and GROK_AUTH_B64, but it does so in the context of legitimate configuration management. It does not attempt to exfiltrate this data; instead, it provides a 'safety gate' to prevent misconfiguration.
  • [COMMAND_EXECUTION]: The skill includes a bash snippet for a 'Minimal real chat probe'. This command is used to verify if the CLI is working correctly and uses standard flags (-p, -m, --effort). It does not execute arbitrary or malicious code.
  • [METADATA_POISONING]: The skill claims to be safe and provides instructions for the analyzer, but these are consistent with its primary purpose of providing a developer utility for a specific CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:20 PM
Security Audit — agent-trust-hub — grok-cli-runtime