Venturebeat5 min read
AI agents don't have to break security controls to go rogue. Here's how to keep them in check
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…
By Badal BhushanVentureBeat AI

Read the full story
Originally published by VentureBeat AI on Nov 1, 2026.
Comments
Sign in to join the discussion.