high-end-visual-design
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides UI/UX design instructions, archetypes, and persona-based guidelines. No malicious code, credential harvesting, or unauthorized system access patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill serves as a template for generating user interface code based on external user prompts. This represents an attack surface for indirect prompt injection.
- Ingestion points: User-provided prompts requesting UI or layout designs.
- Boundary markers: None present; the skill does not define clear delimiters to separate user data from design instructions.
- Capability inventory: The skill is limited to generating UI code (React, Tailwind CSS). It does not contain capabilities for file writing, network operations, or subprocess execution.
- Sanitization: No specific sanitization or filtering logic is provided for user-supplied input.
- [EXTERNAL_DOWNLOADS]: The skill references external design assets including premium fonts (Geist, Clash Display, Plus Jakarta Sans) and lightweight icon libraries (Phosphor Light, Remix Line). These are listed as aesthetic requirements for the generated code rather than automated runtime downloads or installations.
Audit Metadata