ab-testing

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes instructions for running a local Python script scripts/sample_size.py to calculate experimental sample sizes. The script uses standard statistical formulas and the built-in argparse and math libraries. The command execution is limited to this specific, locally-bundled script for its intended analytical purpose.
  • [DATA_EXPOSURE]: The skill checks for the existence of .agents/marketing-context.md at skill load time to incorporate project-specific context. This is a standard practice for tailoring agent behavior to the local environment and does not involve accessing sensitive system files or credentials.
  • [NO_CODE]: Beyond the specific sample size calculation script, the skill primarily consists of high-level methodology, templates, and frameworks for experimentation governance. The logic is instructional rather than executable.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:55 AM
Security Audit — agent-trust-hub — ab-testing