frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied frontend requirements and context to generate production-grade code, which creates a surface for potential indirect instruction injection.
- Ingestion points: User-provided descriptions of components, pages, applications, and technical constraints within the agent interaction flow.
- Boundary markers: The instructions do not define specific delimiters or guidelines to help the agent distinguish between design requirements and potential malicious instructions embedded in the user input.
- Capability inventory: The skill enables the generation of functional, production-grade code (HTML, CSS, JS, React, Vue).
- Sanitization: The skill lacks instructions for sanitizing or escaping user-provided content before it is processed or interpolated into code generation tasks.
Audit Metadata