ab-test-setup
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script (
scripts/sample_size_calculator.py) designed to calculate required sample sizes for experiments. The script is entirely self-contained, using only Python's standard library (math,argparse,json,sys). It does not perform any network requests, file system modifications, or subprocess executions. - [INDIRECT_PROMPT_INJECTION]: The instructions advise the agent to read context from
.claude/product-marketing-context.mdif it exists. While this is an ingestion point for external data, the skill lacks any high-privilege capabilities (like network access or arbitrary code execution) that would allow for exploitation via this vector. - [EXTERNAL_DOWNLOADS]: The skill provides links to well-known third-party A/B testing tools and calculators (e.g., Evan Miller, Optimizely, VWO). These are provided as reference links for the user and are not accessed or executed by the skill itself.
- [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected in the instructions, metadata, or supporting scripts.
Audit Metadata