The Independent
Voice on AI

Badal Bhushan

Badal Bhushan is a Distinguished Engineer and cybersecurity leader specializing in enterprise identity, Zero Trust, and agentic AI security, with more than two decades of experience designing large-scale authentication, authorization, and security architecture.

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

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 public open-source repository, to launching a social engineering campaign targeting a maintainer for approval.