web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • External Downloads: The skill retrieves design and accessibility rules from an external repository (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md). This fetch operation targets a well-known repository structure to ensure that compliance checks are performed against the latest standard guidelines.
  • Indirect Prompt Injection Surface: The skill evaluates external or user-provided files, which introduces a potential data ingestion surface area.
  • Ingestion points: The skill ingests local UI files or code patterns provided by the user for compliance verification (SKILL.md).
  • Boundary markers: There are no specific delimiters or instructions defined in the current workflow to isolate untrusted code content from the agent's core instructions.
  • Capability inventory: The skill's capabilities are restricted to reading files and outputting analysis results in a structured text format (file:line), without any file modification, system configuration, or command execution capabilities.
  • Sanitization: No explicit sanitization or filtering of the input text is described prior to interpretation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:11 AM
Security Audit — agent-trust-hub — web-design-guidelines