database-schema-designer

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses instructional prompts to define the agent's role as a database architect. These instructions include security constraints that explicitly forbid the agent from generating code that stores cleartext passwords, tokens, or other sensitive secrets in the database.
  • [COMMAND_EXECUTION]: The skill documents the use of standard development tools like npx prisma-erd-generator and @dbml/cli for generating ER diagrams and converting schema formats. These are legitimate, industry-standard utilities used within developer workflows.
  • [EXTERNAL_DOWNLOADS]: Referenced Node.js packages, including @faker-js/faker and @paralleldrive/cuid2, are well-known and trusted libraries used for generating mock data and unique identifiers in development environments.
  • [CREDENTIALS_UNSAFE]: The skill's code examples demonstrate the use of password hashing (e.g., hashPassword('password123')) rather than cleartext storage, and it explicitly instructs the agent to avoid hardcoding secrets in generated schemas.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — database-schema-designer