The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains technical documentation and code examples without any instructions that attempt to override agent behavior, bypass safety filters, or extract system prompts.
[DATA_EXFILTRATION]: No evidence of sensitive data access or exfiltration was found. Network operations mentioned (e.g., fetch, WebSocket) are standard examples for local API interaction within web applications.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or private keys were detected. The skill follows best practices by not including sensitive information in its examples.
[EXTERNAL_DOWNLOADS]: The documentation references standard package installations for 'sonner' and 'next-themes' using established tools like pnpm and the shadcn CLI. These are well-known dependencies in the React ecosystem.
[COMMAND_EXECUTION]: Included commands are limited to standard developer workflows for package management and project initialization (e.g., pnpm add, shadcn add).
[REMOTE_CODE_EXECUTION]: No patterns of downloading and executing scripts from untrusted remote sources were identified.
[OBFUSCATION]: The skill uses clear, human-readable text and standard code formatting. No base64, zero-width characters, or other obfuscation techniques were found.

shadcn-syntax-toast-sonner