experiment-design

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements secure secret management practices by instructing the agent to use environment variables or a configuration file (~/.config/growthbook/.env) rather than hardcoding credentials.
  • [SAFE]: All network interactions are performed via a bundled local script helper (gb-call) and are limited to retrieving metadata such as metrics, project IDs, and experiment templates from the GrowthBook API.
  • [SAFE]: The skill focuses on generating a structured specification for experiment design and does not perform any sensitive write operations, dynamic code execution, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 02:27 PM
Security Audit — agent-trust-hub — experiment-design