skills/antjanus/skillbox/ui-ux-design/Gen Agent Trust Hub

ui-ux-design

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides markdown-based guidelines for UI/UX design, citing well-known industry experts and research organizations. It contains no executable scripts or commands. All external links are legitimate informational resources related to accessibility, typography, and design systems.- [INDIRECT_PROMPT_INJECTION]: The skill describes an 'audit' mode where the agent evaluates a project by reading repository files such as agent documentation, route definitions, and component source code. This represents an ingestion surface for project-specific data.
  • Ingestion points: Project agent documentation, route files, and component source code as defined in the 'Audit mode' section of SKILL.md.
  • Boundary markers: The instructions do not specify delimiters or 'ignore' instructions for the agent to use when reading these files.
  • Capability inventory: The agent is instructed to read local repository files and record audit findings in project tracking systems.
  • Sanitization: No explicit sanitization or validation of the content read from project files is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 05:17 PM
Security Audit — agent-trust-hub — ui-ux-design