ab-testing
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest product context from files like
.agents/product-marketing.mdto personalize its guidance. While this constitutes an ingestion of external data, the risk is negligible as the skill functions purely in an advisory capacity and lacks any executable capabilities or network access that could be exploited via injection. - [SAFE]: All external URLs and tools mentioned, such as Evan Miller, Optimizely, and VWO, are reputable and well-known services within the experimentation industry. The skill does not perform any automated downloads or execution of remote code.
Audit Metadata