Agent Security
Secure your agent ecosystem by verifying every agent identity and enforcing real-time security to stop unauthorized actions as you scale from pilot to production.
AI is acting autonomously across the enterprise, while adoption has expanded from pilots to broad-scale deployments. You need a solution that scales with the speed and complexity of agentic AI.
shadow AI.
Get full visibility into every AI agent, app and model, and identify how they connect across your environment.
new risks.
Continuously test AI apps and agents, control permissions and monitor overall security posture in real time.
against threats.
Secure AI interactions and enforce AI-specific controls to stop runtime threats before they have real world impact.
We’re innovating at the speed of AI. Check out the newest features and updates in Prisma AIRS.
Automatically refreshes OAuth tokens
March 2026
Redirects workload traffic to NGFW
March 2026
Supports single image for AIRS
March 2026
Supports HSF on Linux/KVM
March 2026
Supports multi-turn red teaming attacks
February 2026
Profiles AI endpoints for assessments
February 2026
Tests autonomous and multi-agent systems
February 2026
Displays threat snippets in violations
February 2026
Classifies toxicity into eight categories
February 2026
Secures models in Microsoft Foundry
February 2026
Displays AI API security violations
February 2026
Supports token-based API licensing
February 2026