The Agent Skills Directory

[SAFE]: The skill provides security-positive guidance, such as enforcing input validation (Commandment #8), managing secrets (Commandment #10), and implementing the principle of least privilege for database users.- [PROMPT_INJECTION]: The instructions establish a professional persona and instructional framework for the agent. There are no attempts to override system safety guidelines or manipulate the agent's core instructions.- [EXTERNAL_DOWNLOADS]: References official and widely-used development tools and libraries, including Prisma ORM components and validation libraries like Zod, Valibot, and Yup. These are used for legitimate application development.- [COMMAND_EXECUTION]: Instructions describe the use of standard database administration commands (e.g., mongosh, explain) for the user to manage their infrastructure. These are not executed by the skill automatically.- [CREDENTIALS_UNSAFE]: Code examples use clearly marked placeholders for sensitive information. The skill includes explicit instructions for the secure handling of connection strings in production environment.

skill-prisma-mongo-audit