frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate functional frontend code (HTML, CSS, JS, React, Vue).
- Ingestion points: User-provided frontend requirements, target audience, and project context are ingested in SKILL.md to drive the design process.
- Boundary markers: The skill does not define explicit delimiters or instructions to help the agent distinguish between design specifications and potentially malicious instructions embedded in the user input.
- Capability inventory: The agent generates production-grade web code, including JavaScript, which can be executed in development or preview environments.
- Sanitization: No instructions are provided for sanitizing or escaping user content before it is interpolated into the generated code templates or the agent's reasoning flow.
Audit Metadata