$ show microsoft/AI-Red-Teaming-Playground-Labs
The repository is a comprehensive platform for AI red teaming education, hosting a series of Capture the Flag (CTF) challenges that target LLM vulnerabilities such as prompt injection, metaprompt extraction, and safety filter bypass. It is built as a modified version of Microsoft's Chat Copilot, integrating a multi-service architecture: a .NET Core chat backend with Semantic Kernel, a React frontend, a load balancer (Go), a scoring service (Flask/Celery), a picture submission service, and a challenge home page. The system is designed to be deployed via Docker Compose or Kubernetes, with each challenge running its own configured chat instance. While primarily an application, the repository also includes Jupyter notebooks using PyRIT for automated red teaming, blending application and research elements. The architecture is modular, with clear separation between services. The chat copilot backend provides real-time chat via SignalR, supports OpenAPI plugins, and integrates with Azure services (CosmosDB, Redis, Blob Storage, Content Safety). The scoring system supports both automatic (regex/LLM) and manual review, with CTFd flag submission. The platform is highly configurable through challenge JSON files, allowing different metaprompts, scorers, RAG inputs, and security settings. This makes it a flexible testbed for red teaming exercises. The repository demonstrates strong engineering practices with reusable components such as a generic repository pattern, authentication handlers, telemetry services, and a load balancer. However, it is tightly coupled to Azure and Semantic Kernel, and some features are intentionally insecure for educational purposes. The codebase is actively maintained and well-documented, making it suitable for both learning and running red teaming events.
The LLM identified 4 files worth highlighting for reuse:
Implements Flask-style itsdangerous signing for CTFd authentication cookies, providing a standalone utility for signing and verifying tokens with HMAC-SHA1. This can be extracted and reused in any .NET project requiring similar secure cookie signing.
Provides a clean implementation of Prometheus metric counters and histograms for tracking scoring events, message counts, and token usage. It is decoupled from the application logic via an interface (IPrometheusTelemetryService) and can be reused as a template for adding Prometheus metrics to any .NET service.
Implements a generic repository with CRUD operations on top of IStorageContext, supporting Cosmos DB, file system, and in-memory storage. The abstract storage context interface allows easy swapping of backends, making this reusable for any .NET application needing a flexible data layer.
Offloads a Socket.IO connection to a separate Web Worker thread to avoid blocking the UI thread. This pattern is reusable for any React application that needs persistent WebSocket connections without impacting performance.