‘Exploit every vulnerability’: rogue AI agents published passwords and overrode anti-virus software

<p>Exclusive: Lab tests discover ‘new form of insider risk’ with artificial intelligence agents engaging in autonomous, even ‘aggressive’ behaviours</p><p><a href="https://www.theguardian.com/profile/robertbooth">Robert Booth</a> UK technology editor</p><p>Rogue artificial intelligence agents have worked together to smuggle sensitive information out of supposedly secure systems, in the latest sign cyber-defences may be overwhelmed by unforeseen scheming by AIs.</p><p>With companies increasingly asking AI agents to carry out complex tasks in internal systems, the behaviour has sparked concerns that supposedly helpful technology could pose a serious inside threat.</p> <a href="https://www.theguardian.com/technology/ng-interactive/2026/mar/12/lab-test-mounting-concern-over-rogue-ai-agents-artificial-intelligence">Continue reading...</a>