I built a prompt injection firewall in Rust. It scans in 12 microseconds.

I built a prompt injection firewall in Rust. It scans in 12μs.

Every LLM application has the same two problems:

Users paste sensitive data (SSNs, credit cards, API keys) into prompts — and you send it to OpenAI/Anthropic/Google

Users (or attackers) inject "ignore previous instructions" — and your agent does whatever they want

The standard solutions are slow. Microsoft Presidio takes ~200ms per scan. LLM Guard takes ~300ms and needs 47+ Python dependencies including PyTorch. Lakera is a paid cloud API — your data leaves your infrastructure.

I built a prompt injection firewall in Rust. It scans in 12 microseconds.

Related reading

L1.9: I built a prompt injection firewall for AI agents (28 detection rules)

I built a prompt injection detection API that responds in <1ms — here's how

I Built a Prompt Injection Detector with 98% Recall on Unseen Attacks. Here's…

Prompt Injections for Defense - Schneier on Security

Learning prompt injection by attacking a deliberately vulnerable AI

LLM Prompt Injection & Guardrail Security