The Agent Access Problem: When AI Has the Keys, Who’s Really in Control?

About this episode

The episode discusses the implications of AI agents having access to systems and the associated security risks.

In this episode, we dive into the messy reality of AI agents acting inside your systems and what that means for modern security. We explore the idea of agents as actors with real access—credentials, APIs, and permissions—and why this isn’t as new as it sounds (hint: it’s just applications all over again). We unpack where things actually get risky, from over-permissioned agents to unpredictable behavior driven by prompts, and why “it won’t go rogue” might be missing the point entirely. We also...

People in this episode

Hosts: Izar Tarandach, Matt Coles, Chris Romeo

Topics covered

• AI agents
• security
• permissions
• over-permissioned agents
• unpredictable behavior

Keywords

• AI
• security
• agents
• permissions
• credentials
• APIs
• behavior

Mentioned in this episode

Organizations: AI, APIs, applications

More episodes of The Security Table

• The Agentic Access Problem: When AI Becomes Its Own Administrator · June 3, 2026 · 40 min
• The Tool Creep Problem: When More Security Means Less Security · May 8, 2026 · 42 min
• The Human In The Loop Illusion: Why AI Approvals Are Failing Security · April 30, 2026 · 48 min
• The Mythos Problem: When AI Finds Every Vulnerability · April 15, 2026 · 47 min
• What If AI Never Happened? The AppSec Reality Check · April 8, 2026 · 47 min
• The Evolution Problem: After 100 Episodes, What’s Changed… and What Hasn’t? · April 1, 2026 · 50 min