ab-testing
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external context files such as
.agents/product-marketing.md. While this creates an ingestion surface, the risk is negligible as the skill lacks exploitable capabilities. \n - Ingestion points: Reads local context files like
.agents/product-marketing.md.\n - Boundary markers: None specified.\n
- Capability inventory: The skill is strictly instructional and does not utilize tools for command execution, file modification, or network communication.\n
- Sanitization: None specified.\n- [EXTERNAL_DOWNLOADS]: The skill references several well-known industry-standard tools and statistical calculators, such as those provided by Optimizely and Evan Miller. These are external documentation links for user reference and do not involve automated code execution.
Audit Metadata