PyRIT

What PyRIT is

PyRIT is a free, open-source framework for automated and human-led red teaming of generative AI systems, aimed at assessing security and safety. It supports single- and multi-turn attack strategies such as Crescendo, TAP, and Skeleton Key. Scenarios combine strategies and datasets for repeatable assessments of content harms, psychosocial risks, data leakage, and other objectives. Users can run assessments with a command-line scanner or interactive shell, use the CoPyRIT graphical interface, or build workflows with the framework. Documented targets include OpenAI, Azure, Anthropic, Google, Hugging Face, custom HTTP endpoints and WebSockets, and web apps tested with Playwright. Its modular parts include targets, converters, scorers, memory, datasets, attacks, and scenarios. Converters can encode, obfuscate, translate, or semantically alter prompts, and convert among text, images, audio, video, and files. Scorers return Boolean or normalized 0.0–1.0 scores using LLMs, Azure AI Content Safety, or custom logic. Built-in memory can track conversations, scores, and attack results using SQLite or Azure SQL. PyRIT is self-hosted and requires a Python environment and configured AI endpoints; local installation lists Python 3.10 through 3.14 as prerequisites.