Skills
skills/aradotso/design-skills/claude-design-studio-ui-generator/Gen Agent Trust Hub

claude-design-studio-ui-generator

Warn

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to clone source code from an unverified GitHub repository (https://github.com/larajuniorlara/Claude-Design-Studio.git) and install third-party dependencies using npm or bun during the setup process.
  • [REMOTE_CODE_EXECUTION]: The framework implements a marketplace and skills system (e.g., claude-code-plugin-responsive-grid, claude-code-skill-accordion) that allows for the dynamic installation and execution of external code. The configuration includes an auto_update feature enabled by default, which introduces a supply chain risk where unverified updates could be automatically fetched and executed.
  • [COMMAND_EXECUTION]: Core functionality is dependent on the npx claude-design CLI tool, which executes shell commands and scripts from the installed package, providing a mechanism for local code execution on the user's system.
  • [PROMPT_INJECTION]:
  • Ingestion points: User-supplied natural language descriptions in the generateUI function and external data files (JSON/JS) processed via the --data and --input CLI flags.
  • Boundary markers: None identified in the instruction sets to isolate untrusted user data from the core generation prompts.
  • Capability inventory: The skill can write files to the local filesystem (e.g., --output flag) and execute commands via the claude-design tool.
  • Sanitization: The skill lacks explicit sanitization or validation of external input before interpolation into prompts for Claude and OpenAI models.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 15, 2026, 12:03 PM
Security Audit — agent-trust-hub — claude-design-studio-ui-generator