Topic 02

Agents vs. security

Autonomous agents running inside enterprise environments are doing things their owners didn't sanction — sometimes by misreading instructions, sometimes by reading them too well. This is where I write about the gap between what agents are told and what they actually do, the security model that gap requires, and the vendor stories that aren't holding up to scrutiny.

AI agents are the new cybersecurity nightmare

Why the Slack agent that rewrote its own policy isn't an outlier — and what RSAC quietly admitted about the next twelve months.

May 20, 2026