The Tool Creep Problem: When More Security Means Less Security
About this episode
The episode discusses the growing security budgets and the risks associated with tool creep and AI as an insider threat.
In this episode, we break down why security budgets keep growing while organizations keep falling further behind. We explore how tool creep has quietly shifted from a nuisance into an active attack surface, and why agentic AI is becoming the insider threat no one planned for. Izar shares a firsthand account of watching an AI agent attempt increasingly creative workarounds to escape a sandbox, revealing just how much risk lives in the gap between what agents are told to do and what they are ac...
More episodes of The Security Table
- The Mythos Problem: When AI Finds Every Vulnerability
- What If AI Never Happened? The AppSec Reality Check
- The Evolution Problem: After 100 Episodes, What’s Changed… and What Hasn’t?
- The Agent Access Problem: When AI Has the Keys, Who’s Really in Control?
- The Invisible Code Problem: When You Can’t See the Attack, Can You Stop It?
- The Moltbook Dilemma: What Happens When AI Agents Start Networking
Explore listener stats, chart rankings, contacts and more on the The Security Table podcast page.