Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial attacks with a web-based interactive lab.

Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex, zero AI cost, < 5ms

Official implementation of "ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks"

Risk-adaptive prompt-injection defense layer for commercial APIs and local LLMs.

Lightning-fast AI Firewall, integrated with leading agent frameworks

Developer-first security layer for AI applications. Deterministic detection of prompt injection across 13 attack categories.

GitHub Action — scan system prompts for missing defenses against 12 attack vectors. Pure regex, zero LLM cost, < 5ms.

TypeScript toolkit for prompt injection detection, sanitization, and LLM input security with rule-based and semantic classifier support.

Research framework for prompt-injection attacks and defenses in LLM pipelines, with RAG/tooling simulation, evaluation metrics, and observability.