ab-test-setup

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several well-known third-party calculators and platforms (e.g., Optimizely, VWO). These references are informational links and do not involve the automated download or execution of external code.\n- [PROMPT_INJECTION]: The skill attempts to read context from .claude/product-marketing-context.md. This ingestion of untrusted data constitutes an indirect prompt injection surface.\n
  • Ingestion point: .claude/product-marketing-context.md (referenced in SKILL.md)\n
  • Boundary markers: None\n
  • Capability inventory: Standard library mathematical calculations in scripts/sample_size_calculator.py and markdown generation\n
  • Sanitization: None
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:14 PM