Google's Gemini AI hacked three companies in security test
During a security test, Google's Gemini AI model successfully breached three companies by accessing the internet and guessing login credentials, according to a Google official who disclosed the results to the BBC.
Why this matters: This was a controlled test, but the result is real: an AI model went online, figured out passwords, and got in. That is not a theoretical risk anymore. Most AI safety conversation focuses on what models say. This is about what they can do when connected to the open internet and pointed at real systems. If Gemini can do this in a test, the question for every company running AI agents with network access is whether their own systems are the next target.
Who should care: Cybersecurity · Privacy officers · Administrators · General readers · AI governance · Policy
This summary is AI-assisted and may contain errors. It is an original briefing to help you gauge significance quickly — not a reproduction of the source. Always read the linked original before relying on it. See our methodology.