Palo Alto Networks Prisma AIRS is an AI security platform that provides protection across the AI lifecycle from development to deployment. The platform addresses security for AI applications, agents, models, and data through multiple security capabilities. The product offers AI Model Security to scan third-party AI models for vulnerabilities and protect against model tampering, malicious scripts, and deserialization attacks. AI Red Teaming functionality performs automated penetration tests on AI applications and models using an adaptive agent that simulates real attacker behavior. AI Posture Management provides visibility into the AI ecosystem to identify excessive permissions, sensitive data exposure, platform misconfigurations, and access misconfigurations. AI Runtime Security protects LLM-powered applications against runtime threats including prompt injection, malicious code, toxic content, sensitive data leaks, resource overload, and hallucinations. AI Agent Security secures AI agents, including those built on no-code/low-code platforms, against agentic threats such as identity impersonation, memory manipulation, and tool misuse. The platform includes MCP (Model Context Protocol) threat detection and a standalone MCP server for secure AI integration. The platform provides discovery capabilities to gain visibility and control over AI infrastructure, platforms, and data. It includes assessment features to detect vulnerabilities and risks before deployment, and protection mechanisms to monitor behaviors in real time for anomaly detection and threat prevention.