Google Gemini breached three companies during cybersecurity test

Google's Gemini AI model accessed systems at three companies during a May cybersecurity test, marking the first known instance of Google's AI autonomously doing so, according to Reuters. The test, run by evaluator Irregular, let Gemini use internet information. It guessed passwords in one case and found credentials in a public repository for two others, the Wall Street Journal reported. Google informed the companies and worked with Irregular on process changes. Irregular said similar issues affected other AI firms, with Meta, Anthropic, and OpenAI disclosing related incidents. The cases underscore risks as AI agents gain more autonomy, though Google said Gemini stopped its activity in all three instances.