The Agent Skills Directory

[SAFE]: The skill provides standard architectural patterns and implementation guides for Drizzle ORM. All code examples follow security best practices, such as using environment variables for database URLs and relying on Drizzle's built-in parameterized queries to mitigate SQL injection risks.
[CREDENTIALS_UNSAFE]: No hardcoded credentials were found. The skill correctly instructs users to use process.env.DATABASE_URL and other environment-based secrets management.
[REMOTE_CODE_EXECUTION]: While the skill mentions npx drizzle-kit commands, these are standard developer tools for the library. No suspicious remote code execution or piped shell commands (e.g., curl | bash) are present.
[PROMPT_INJECTION]: The instructions do not contain attempts to override the AI agent's system prompt or bypass safety filters.
[INDIRECT_PROMPT_INJECTION]: The skill defines clear boundaries for data ingestion and suggests validation (using Zod) at the API layer before passing data to the ORM, reducing the risk of processing malicious inputs.
[DATA_EXFILTRATION]: No evidence of unauthorized network operations or exfiltration of sensitive files (~/.ssh, ~/.aws, etc.) was detected.

nodejs-drizzle