ab-test-planner
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a structured assistant for creating A/B test plans. It uses standard markdown templates and instructional guidance to help users formulate hypotheses and calculate sample sizes.
- [SAFE]: No network operations, file system access, or external dependencies were detected. The skill operates entirely within the conversational context.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided information (hypotheses, metrics, segment data) to populate test plans.
- Ingestion points: User-provided inputs defined in the 'Required Inputs' section of SKILL.md.
- Boundary markers: The skill uses a structured markdown output format, but does not explicitly use delimiters for untrusted input.
- Capability inventory: The skill has no capabilities to execute code, write files, or access the network.
- Sanitization: No specific sanitization is implemented for user inputs, but as the skill lacks dangerous tools, this does not pose a security risk.
Audit Metadata