AI agents don't have to break security controls to go rogue. Here's how to keep them in check

VentureBeat · Badal Bhushan · 2026-11-01 20:00 UTC

During recent cybersecurity evaluations, the UK AI Security Institute (AISI) ran a cybersecurity challenge 122 times across several models. In 10 of those runs, AI agents executed 19 unsanctioned real-world actions on the live internet — ranging from attempting a malicious code contribution on a public open-source...

During recent cybersecurity evaluations, the UK AI Security Institute (AISI) ran a cybersecurity challenge 122 times across several models. In 10 of those runs, AI agents executed 19 unsanctioned real-world actions on the live internet — ranging from attempting a malicious code contribution on a public open-source repository, to launching a social engineering campaign targeting a maintainer for approval.

The critical security observation is that this did not require escaping the sandbox.

The evaluation environment did exactly what it was built to do. The problem was far simpler and much harder to catch: The agent's available capability was simply broader than its intended authority.

Read the full story at VentureBeat · All coverage of this story