Scammers are out of control. Every year, fraudsters and cybercriminals make billions by tricking people into parting with their cash. Romance fraud, business email compromise, investment scams, sextortion--the list of ways criminals prey on people is virtually endless and constantly changing. Add to that impersonation scams, where a criminal pretends to be someone known to their target and extracts money. There have been increasing calls for people, and particularly families, to create passphrases or passwords with each other.

Generative Artificial Intelligence (GenAI) is becoming ubiquitous in our daily lives. The increase in computational power and data availability has led to a proliferation of both single- and multi-modal models. As the GenAI ecosystem matures, the need for extensible and model-agnostic risk identification frameworks is growing. To meet this need, we introduce the Python Risk Identification Toolkit (PyRIT), an open-source framework designed to enhance red teaming efforts in GenAI systems. PyRIT is a model- and platform-agnostic tool that enables red teamers to probe for and identify novel harms, risks, and jailbreaks in multimodal generative AI models. Its composable architecture facilitates the reuse of core building blocks and allows for extensibility to future models and modalities. This paper details the challenges specific to red teaming generative AI systems, the development and features of PyRIT, and its practical applications in real-world scenarios.