The Agent Skills Directory

[SAFE]: The skill serves as a technical reference guide for developing Node.js and Bun backend applications using modern security and architectural best practices.
[CREDENTIALS_SAFE]: While various configuration examples mention secrets (e.g., DATABASE_URL, JWT_SECRET), they are used as descriptive placeholders or in the context of environment variable validation logic. The skill explicitly instructs developers to keep .env files out of version control and never to log or hardcode secrets.
[EXTERNAL_DOWNLOADS]: The skill mentions various well-known production-grade Node.js and Bun packages (e.g., express, pino, prisma, zod). These references are standard for the development domain and do not involve suspicious download or execution patterns.
[COMMAND_EXECUTION]: The skill permits the use of the Bash tool to perform development tasks such as running tests (vitest, bun test), linting, and building Docker images. These operations are consistent with the skill's purpose as an engineering aid.
[INDIRECT_PROMPT_INJECTION]: The skill maintains a low vulnerability surface by focusing on providing reference material. It reinforces security boundaries by instructing the agent to implement strict validation in the code it produces.

nodejs