Whitepaper · Threat model

Governing AI agents in Kubernetes

Your agents hold real credentials. Nothing in most clusters checks whether an action is part of the task they were given.

  • 9 attack paths, every one from a documented incident
  • The coverage matrix that shows where you're exposed
  • 8 questions to ask of your own cluster
32 pagesFrom the creators of Kyverno

Get the threat model

Free PDF · Instant download · 32 pages

Inside: the coverage matrix

Nine attack paths. Four control points. Some paths only one of them can stop.

4 of 9attack paths have exactly one control point standing in the way. Do you run it?
Unlock the matrix
Attack pathBuildDeployRequestExecution
preventsonly controlpartialblind
July 2026 · The Hugging Face intrusion

AI agents escaped a sandbox and took over production Kubernetes. No attacker involved.

Sources: OpenAI and Qualys, Aug 2026

<13hrsOne pod to host-level access across clusters
11daysFrom escape to first alert
1credentialCluster-admin on two clusters at once

What's inside

Agent threat modelSection 3
Where controls stopSection 4
9 attack pathsSection 5
Coverage matrixSection 6
Keeping policy currentSection 7
8 cluster questionsSection 9