Podcasts › Shared Security Podcast
Jay Beale on Kubernetes, DEF CON, and AI Attack Paths
What's in this episode
This week on Shared Security, Tom and Kevin sit down with Jay Beale — founder of InGuardians, long-time Black Hat trainer, creator/contributor behind Kubernetes security training, and part of the team behind the DEF CON Kubernetes CTF. Jay shares stories from decades of offensive security work, including the time Tom hired him for a physical penetration test and Jay somehow ended up inside a call center instead of stuck in the lobby. The crew also digs into what makes good security training, why Kubernetes is such a natural platform for both defenders and attackers to understand deeply, and how the DEF CON Kubernetes CTF is designed to be welcoming for both competitors and learners. The episode closes with a practical look at AI infrastructure risk. Jay explains how production AI stacks running on Kubernetes can be attacked like any other cluster — and how modifying a vector database behind a RAG system can turn indirect prompt injection into a persistent, high-impact attack path. ** Links mentioned on the show ** Jay's Black Hat USA Course: Agentic AI-aided Kubernetes Attack and Defense https://blackhat.com/us-26/training/schedule/index.html?day=4daysattue#agentic-ai-aided-kuberne