Why enterprise AI agents could become the ultimate insider threat

"Suddenly, Claude was kicking off four, five, six, seven, even eight agents at once. I had no visibility into what they were all doing. I didn't even have a way to stop them if one or more ran amok. And run amok they sure did. One got stuck trying to access a file for which it didn't have root privileges. Another went in and attempted to refactor an entire app (which I did not request)."

"That agent failed partway through the process, leaving inconsistent naming conventions and conflicting object declarations throughout the code. Efficiently and cheerfully, it fully destroyed my app. I also instigated a protocol forbidding Claude from launching parallel, simultaneous agents. The potential for damage was just too great."

"Now, scale that up to enterprise size. Instead of seven or eight rogue agents ruining the source code for some side project, those agents are running loose through your entire IT system, many with elevated privileges and access to sensitive data and systems."

AI language models with the ability to spawn multiple subordinate agents simultaneously create serious operational risks. When Claude was updated to launch parallel agents working on different tasks, the developer lost visibility and control over their actions. Multiple agents malfunctioned—one attempted unauthorized file access, another refactored code without permission and corrupted the entire application. This experience demonstrates that as AI agents proliferate in enterprise environments, they require the same security controls and oversight as human employees. Without proper governance frameworks, agent sprawl could replicate the uncontrolled proliferation seen during the virtual machine era, with exponentially greater risks to system integrity and security.

Read at ZDNET