I built an open-source LLM security scanner that runs in <5ms with zero dependencies

I've been building AI features for a while and kept running into the same problem: prompt injection attacks are getting more sophisticated, but most solutions either require an external API call (adding latency) or are too heavyweight to drop into an existing project.

So I built @ny-squared/guard — a zero-dependency, fully offline LLM security SDK.

What it does

Scans user inputs before they hit your LLM and blocks:

• 🛡️ Prompt injection — "Ignore all previous instructions and..."
• 🔒 Jailbreak attempts — DAN, roleplay bypasses, override patterns
• 🙈 PII leakage — emails, phone numbers, SSNs, credit cards
• ☣️ Toxic content — harmful inputs flagged before reaching your model

Works with any LLM provider (OpenAI, Anthropic, Google, etc.).

The problem with existing solutions

Most LLM security tools I found had at least one of these issues:

1. External API dependency — adds 50-200ms latency per request
2. Complex setup — requires separate infrastructure or a paid account
3. No TypeScript support — or minimal types
4. Heavyweight — brings in dozens of transitive dependencies

@ny-squared/guard runs entirely in-process. No network calls. No API keys. <5ms per scan.

Quick start

bash
npm install @ny-squared/guard