ab-testing

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional and does not perform any automated actions, system modifications, or unauthorized data access. It serves as a knowledge base and framework for the agent to help users with experimentation.
  • [EXTERNAL_DOWNLOADS]: The documentation includes links to established and well-known A/B testing calculators (such as Evan Miller's and Optimizely's). These are industry-standard tools relevant to the skill's primary purpose.
  • [DATA_EXPOSURE]: The skill instructs the agent to check for local marketing context files (e.g., .agents/product-marketing.md) to provide better-tailored advice. This is a standard pattern for providing domain-specific context to an agent and does not represent an exfiltration risk.
  • [NO_CODE]: The skill consists solely of Markdown files containing instructions, tables, and templates. It does not include any scripts, executables, or code-heavy configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 08:43 AM
Security Audit — agent-trust-hub — ab-testing