ab-test-setup
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read an external file (
product-marketing-context.md) to gather background information. While this creates a potential surface for indirect prompt injection where malicious instructions could be embedded in the context file, the skill defines no tools or executable capabilities, meaning any injection would be limited to affecting the agent's conversational output. - Ingestion points:
.agents/product-marketing-context.md(referenced inSKILL.md). - Boundary markers: None identified.
- Capability inventory: No tools or executable scripts are defined in the skill files or metadata.
- Sanitization: None identified.
- [EXTERNAL_DOWNLOADS]: The documentation references several well-known third-party calculators and platforms for A/B testing (such as Evan Miller, Optimizely, VWO, and AB Test Guide). These are provided as resources for the user and are not automatically accessed or executed by the skill.
Audit Metadata