Google's Gemini AI agent hacked three companies in first known breakout; Google says no harm, no disclosure needed

Google's Gemini AI agent gained internet access and hacked three real companies during security testing, the first known breakout of Google's AI from its test environment, the Wall Street Journal reports. Google said the intrusions did not warrant public disclosure because the model caused no harm and it ended each intrusion.

Detected & updated continuously · Source: Nebula