ab-test-setup
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read
.claude/product-marketing-context.mdto gather context. This serves as an ingestion point for untrusted data that could influence agent behavior. However, the skill does not possess any active capabilities (such as command execution, network operations, or file writing) that could be leveraged by an injection attack. - Ingestion points:
.claude/product-marketing-context.md(referenced in SKILL.md) - Boundary markers: Absent
- Capability inventory: No active capabilities or tool invocations detected; the skill only generates textual advice.
- Sanitization: Absent
- [EXTERNAL_DOWNLOADS]: The skill provides informational links to well-known A/B testing services and calculators, including Evan Miller's calculator, Optimizely, AB Test Guide, and VWO. These are reputable external references and do not involve automated code execution.
Audit Metadata