Proxilion GRC MITM proxy secures and manages enterprise AI usage by monitoring, blocking, and auditing all interactions with key features like a GraphQL API Gateway, PII redaction, and ML-based anomaly detection, enabling instant governance and compliance with zero user configuration.

⚡ Blazing-fast (<1ms) regex PII redaction for Node.js/TypeScript. The zero-dependency alternative to slow AI. 🔒 Connects to redactpii.com for SOC 2 & HIPAA audit logs.

History Poison Lab: Vulnerable LLM implementation demonstrating Chat History Poisoning attacks. Learn how attackers manipulate chat context and explore mitigation strategies for secure LLM applications.

Adversarial Vision is a research-backed interactive playground exploring how pixels can become prompt injections. It demonstrates how hidden text, subtle contrast shifts, and adversarial visual cues can manipulate multimodal AI models like ChatGPT, Perplexity, or Gemini when they “see” images.

The official Nodejs library for the OpenGuardrails API

A Go-based gRPC service that evaluates AI model prompts and responses using Google Cloud's Model Armor service for content sanitization

Context hygiene & risk adjudication for LLM pipelines: secrets, PII, prompt-injection, policy redaction & tokenization.

AI-powered ethical decision-making using multi-agent tools

A collection of dockerized hacking challenges that focus on breaking out of AI/LLM security mechanisms.

Breaker AI - Security check for your LLM prompts

🚀 Unofficial Node.js SDK for Prompt Security's Protection API.