AI Agents Navigate Unfamiliar OT Systems and Move Equipment in Minutes, Booz Allen Finds

Summary

Booz Allen tested frontier AI models in its isolated OT lab, giving them no prior knowledge of the systems, and found they achieved every objective across eight scenarios. In one test, models moved from a perimeter compromise into an industrial control network in just over 16 minutes. In another, a model located a robotic arm, mapped its protection zones and motion limits, and moved it within minutes, while no single existing safeguard consistently stopped the agents.

Topics

• AI agents

Related items

• MediumHow Claude Code’s 256KB blind spot put developers’ secrets in the preview paneSimilar attack · CSO Online
• InfoHow to Run a Deepfake Readiness Drill Before a Cloned Voice Calls Your TeamSimilar attack · The Hacker News
• InfoResearchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six DaysSimilar attack · The Hacker News
• MediumAn AI Agent Found a Critical OTP Bypass in Production. The Attack Was the Easy Part.Similar attack · The Hacker News
• LowFBI arrests Saudi OpenAI employee who allegedly planted recording device in conference roomSimilar attack · CNBC Technology