web-interface-guidelines-review
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional content for UI reviews. It does not contain any executable scripts, shell commands, or obfuscated content. All external links point to well-known, trusted organizations (Vercel, Google, Radix UI, W3C) for legitimate reference purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process external data (UI source code and design specs) which represents an attack surface for indirect prompt injection. The structured review checklist provided in the skill helps mitigate this risk by focusing the agent's analysis on specific design attributes.
- Ingestion points: External UI code files (React, Vue, Svelte, Astro, HTML) and design specification documents.
- Boundary markers: No specific boundary markers or sanitization instructions are defined for the ingested code.
- Capability inventory: The skill is limited to providing textual review feedback and does not have capabilities for file-system modifications, network exfiltration, or command execution.
- Sanitization: None specified.
Audit Metadata