ab-test-setup
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown files for documentation and templates; no scripts or executable files are included.\n- [PROMPT_INJECTION]: The skill directs the agent to read context from .claude/product-marketing-context.md, which represents a surface for indirect prompt injection if the file is supplied by an untrusted source.\n
- Ingestion points: .claude/product-marketing-context.md is read during the initial assessment phase as described in SKILL.md.\n
- Boundary markers: Absent; there are no instructions to the agent to treat the context as untrusted data.\n
- Capability inventory: None; the skill has no scripts for executing code, making network requests, or modifying files.\n
- Sanitization: Absent; no validation is performed on the input file content.\n- [SAFE]: The skill links to reputable A/B testing resources and calculators from well-known services (e.g., Evan Miller, Optimizely, VWO). These references are neutral and provide helpful external tools for the user.
Audit Metadata