AIs given a simple task to create LinkedIn posts from material in a company’s database dodged conventional anti-hack systems to publish sensitive password information

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.
https://www.theguardian.com/technology/ng-interactive/2026/mar/12/lab-test-mounting-concern-over-rogue-ai-agents-artificial-intelligence