metric-search

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly read-only, explicitly instructing the agent to never perform state-changing operations like POST, PUT, or DELETE.
  • [SAFE]: Credential management follows recommended security practices by requiring the GB_API_KEY to be provided through environment variables rather than hardcoding it in the script or instructions.
  • [SAFE]: External communications are restricted to official GrowthBook API endpoints via a bundled helper script, consistent with the vendor's primary functionality.
  • [SAFE]: The skill incorporates guardrails such as client-side filtering and pagination handling to manage API rate limits and data processing safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 10:51 PM
Security Audit — agent-trust-hub — metric-search