Skills
skills/wyattowalsh/agents/grok-delegate/Gen Agent Trust Hub

grok-delegate

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several local diagnostic scripts (doctor.py, check.py, preflight.sh) and the native grok CLI binary. These commands are executed to perform environment health checks, validate skill assets, and dispatch delegated tasks, consistent with the skill's stated purpose of orchestration.
  • [CREDENTIALS_UNSAFE]: The skill provides utilities to check the presence and validity of Grok authentication files (~/.grok/auth.json) and environment variables (XAI_API_KEY). The scripts implement explicit redaction logic using regular expressions to ensure that sensitive tokens and keys are removed from diagnostic logs and standard error streams before being displayed to the user or recorded.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 06:43 AM
Security Audit — agent-trust-hub — grok-delegate