The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No instructions attempting to override agent behavior, bypass safety filters, or extract system prompts were found. The content is purely educational and technical.
[DATA_EXFILTRATION] (SAFE): Connection strings and API tokens are correctly handled via environment variables (e.g., process.env.DATABASE_URL). There are no hardcoded secrets or unauthorized network exfiltration patterns.
[EXTERNAL_DOWNLOADS] (SAFE): The documentation references installation commands for legitimate, well-known libraries within the Node.js ecosystem (e.g., drizzle-orm, @upstash/redis). These are standard dependencies for the documented functionality.
[COMMAND_EXECUTION] (SAFE): The code examples use standard ORM methods for database operations. No arbitrary command execution, shell injection, or unsafe subprocess calls were identified.
[OBFUSCATION] (SAFE): No signs of encoding, zero-width characters, homoglyphs, or other techniques designed to hide malicious intent were found in the documentation or code snippets.

drizzle-orm