ab-testing
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill consists of markdown instructions and templates designed to guide an AI agent in experimentation workflows. It does not contain executable code, scripts, or dangerous shell commands.
- [EXTERNAL_DOWNLOADS]: The skill references several well-known and reputable third-party services for A/B testing calculations and tools, including Evan Miller's calculator, Optimizely, VWO, and PostHog. These references are to documentation and calculators and do not involve remote code execution.
- [SAFE]: The instructions direct the agent to read local project context files (such as
.agents/product-marketing.md) to better understand the user's domain. This is a standard instructional pattern for providing project context and does not present a data exfiltration or privilege escalation risk in this implementation.
Audit Metadata