awesome-design-md-jp

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to clone a repository from GitHub (github.com/kzhrknt/awesome-design-md-jp.git) containing design specifications and references Google Fonts for web font implementation.
  • [COMMAND_EXECUTION]: Includes standard shell command examples for environment setup and file management, such as git clone, cp, and open for previewing local HTML files.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface as the skill instructs the agent to follow rules defined in processed data (DESIGN.md files).
  • Ingestion points: Reads content from DESIGN.md in the project root.
  • Boundary markers: None present; the agent is told to follow specifications directly.
  • Capability inventory: The skill uses file system operations (fs.readFileSync) and suggests agent-level integration for UI generation.
  • Sanitization: No sanitization is performed on the design token extraction logic provided in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 03:47 AM