About this episode

The episode discusses the significant security risks posed by AI agents and outlines five major risk categories that security teams need to be aware of.

AI agents can search the web, manipulate files, run commands, make API requests, access cloud platforms, and operate fully autonomously. They are powerful, they are here, and most organizations have no security controls around them whatsoever. In this episode, Brad and Spencer break down the five major AI agent risk categories security teams need to understand right now, using Simon Willison's "lethal trifecta" as a framework and building on it with two additional risk areas they see in the f...

People in this episode

Hosts: Brad, Spencer

Topics covered

• AI agents
• security risks
• autonomous systems
• cloud platforms
• API requests

Keywords

• AI agents
• security controls
• risk categories
• autonomy
• cloud security

Mentioned in this episode

Organizations: SecurIT360

Books & works: Simon Willison's "lethal trifecta"

More episodes of The Cyber Threat Perspective

• Guaranteed way to catch threat actors | Ep 188 · July 17, 2026 · 31 min
• Avoid this cyber leadership trap | Ep 187 · July 10, 2026 · 16 min
• Episode 186: Real Life Active Directory Attack Paths · July 3, 2026 · 36 min
• [Replay] Episode 172: The Biggest Security Blind Spots in Midsized Companies · June 25, 2026 · 34 min

Explore listener stats, chart rankings, contacts and more on the The Cyber Threat Perspective podcast page.