Prisma AIRS AI Red Teaming API

An automated red teaming API for assessing the safety and security of generative AI systems including large language models and LLM-powered applications. The API simulates real-world threats by sending crafted attack prompts including jailbreaks, prompt injection, and input manipulation to target AI systems and evaluating responses. Supports creating scan targets, executing asynchronous vulnerability scans, and retrieving detailed reports.