frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): No sensitive file access or network communication patterns were detected. The skill focuses entirely on client-side code generation.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not perform any external package installations or execute remote scripts. It provides instructions for generating code based on user requirements.
- [Prompt Injection] (SAFE): While the skill uses directive language like 'CRITICAL' and 'IMPORTANT', these are used to emphasize design quality and aesthetic consistency rather than to bypass safety guardrails or extract system prompts.
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted user requirements to generate UI code.
- Ingestion points: User-provided frontend requirements in
SKILL.md. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: Generates HTML, CSS, React, and Vue code.
- Sanitization: None specified. This is a standard risk for code-generation skills and is mitigated by the trusted nature of the author and the context of usage.
Audit Metadata