We built a burrito-ordering AI agent, put it on Kubernetes with scoped cluster access and a live terminal, and let a room of engineers try to break it. It is tons of fun.
Over three rounds they push the agent to steal customer data, deploy malicious workloads, and take the cluster down. Forkbombs anyone!

The first round has nothing protecting the agent, and it usually falls apart in about one prompt.

The second runs the same attacks against an ordinary CNCF platform floor, which blocks most of them, though a few run up a bill before they get stopped.

In the third round attendees switch on the remaining guardrails themselves and watch how the agent's behavior and its token cost change.

Running it taught us that for most shops, AI doesn't create just brand-new security problems it also makes the ones you already have more expensive. Token spend becomes its own denial-of-service vector for example. Most of what your platform already does holds up against an agent (or for an agent), and the gap that's left is smaller and stranger than people assume. This workshop covers the base guardrails as well as that enhanced gap that you must have for AI workloads.

We ran this at AI Engineer World's Fair on June 29th 2026. This version covers what held up, what broke, and what we've changed since. We have made vast improvements including model triage, provisioning and sandboxing (as an option). This will be a very evolved, much more polished, and much more expanded presentation than the one we ran at AI Engineer World's Fair. This will be much more hands-on instead of just a web interface. They will actually get access to their own cluster.

Ozzie the Overconfident Operator has secured his cluster! He has added Role-Based Access Control (RBAC) and carefully given cluster admin privileges to himself alone. As he self-congratulates, Nova the Nefarious Ne'er-do-well watches from around the corner, drooling with anticipation. Spoiler alert⎯Ozzie is about to get HACKED.

In this theatrical play, the speakers perform as Ozzie and Nova, playfully demonstrating Kubernetes security as Nefarious Nova exploits each of Ozzie's oversights. What can Ozzie do when Nova gets the upper hand? How can Ozzie proactively keep Nova's threats at bay?

You’ll laugh out loud while discovering cloud native security concepts including Kubernetes network policies, mutual TLS, admission controller policy enforcement, runtime security, git commit signing, and multi-factor authentication.

Learn security basics alongside Overconfident Ozzie, who is sure the cluster is COMPLETELY secure this time. There is nothing Nova can do to break... uh-oh. Not again!