ab-test-validity-checklist
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a documentation-only resource providing a structured process for human-led A/B test validation. It contains no executable scripts, tool calls, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to analyze experiment proposals and configuration files (e.g.,
experiments/<id>/proposal.yml). - Ingestion points: Markdown and YAML experiment proposals provided in the agent's context.
- Boundary markers: The skill does not define specific delimiters for separating untrusted proposal data from instructions.
- Capability inventory: No automated capabilities (tools, file writes, or network access) are defined in the skill files.
- Sanitization: No sanitization or validation of the input proposal data is performed.
- [EXTERNAL_DOWNLOADS]: The skill includes references to reputable academic research and well-known service documentation. These are documented neutrally as trusted educational resources.
Audit Metadata