An open-source knowledge base of defensive countermeasures to protect AI/ML systems. Features interactive views and maps defenses to known threats from frameworks like MITRE ATLAS, MAESTRO, and OWASP.

AspGoat is an intentionally vulnerable ASP.NET Core application for learning and practicing web application security.

A low-cost approach to testing AI chat experiences and security concepts

Monitor, detect, and analyze security threats and Shadow AI in your LLM applications with comprehensive analytics and real-time alerting.

Vanguard is an Office 365 Add-in for advanced email scanning to prevent malicous attacks on an enterprise scale

Elite-grade JavaScript prompt-injection defense library. Real-time detection, deterministic scoring, and zero-dependency protection for LLMs on the Edge.

Adversarial MCP server benchmark suite for testing tool-calling security, drift detection, and proxy defenses

Contributed by Community

A secure, client-side PII masking tool that redacts sensitive information (emails, names, SSNs) locally in the browser before sending text to LLMs or GPT.

🧠 Monitor web app performance and detect anomalies with AI-driven insights, capturing key events and generating detailed incident reports.

Prompt Inject Demonstration

🏦 AI Security Training Game - Can you breach the AI vault?

Armorly is an open-source Chrome extension that blocks intrusive AI-native ads and sponsored content from all major chatbots (like ChatGPT, Grok, and Perplexity) and provides essential, in-browser hidden prompt injection security.