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