form-cro
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, providing a framework for auditing and improving web forms. It does not contain any executable code, scripts, or configuration for external tools.
- [PROMPT_INJECTION]: The skill is designed to analyze user-provided form schemas and marketing context, which introduces a surface for indirect prompt injection.
- Ingestion points: User prompts containing form details and the local file
.agents/product-marketing-context.md. - Boundary markers: None present.
- Capability inventory: The skill only produces text recommendations; it has no access to shell commands, network requests, or file-writing tools.
- Sanitization: None present.
- Risk: The potential impact is minimal as the agent's output is purely advisory and lacks access to sensitive capabilities.
Audit Metadata