Prisma AIRS Guardrails for agentgateway in 150 Lines of Python
Originally published at webofmike.com on 2026-10-12. The demo repo and every command in it were run before publishing. Plenty of security teams already run Prisma AIRS , Palo Alto's AI runtime security service, and they want every prompt and LLM response checked by it. I wired it into Solo Enterprise for agentgateway on Kubernetes with one policy and a 150-line Python adapter. Injection prompts…
Prisma AIRS integrates with agentgateway, a Kubernetes-based deployment, through a 150-line Python adapter. This integration aims to enforce Prisma AIRS' AI runtime security policies on LLM responses. The adapter translates Prisma AIRS' API format to fit agentgateway's webhook format, masking sensitive data like SSNs and card numbers.
If Prisma AIRS is unreachable, agentgateway fails closed, preventing LLM calls. The adapter, deployed in a separate namespace, forwards the caller's ID for reporting. The whole setup requires only a single policy manifest on the gateway side, streamlining security enforcement.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
