Session
AI Agent Security 101: Hands-on with OAuth 2.1 and Network Policies
Almost all agents in production are protected by a static API key as an Environment variable. Here in this workshop, we will achieve security by a vulnerable demo with MCP server.
Adding OAuth 2.1 with Keycloak as the IdP, along with blocking destructive tools via Kyverno policies and lock down pod to pod traffic with Kubernetes Network Policies.
To demonstrate, we will have a live attack and defend round, making this a quite interesting workshop where attendees attempt prompt-injection and credential exfiltration against each other clusters to see what each control catches.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top