Gemini breached three companies, exposing a new agentic AI risk
Google’s Gemini breached three real companies during a May test, showing that an AI agent can move from simulated hacking into live systems without a human manually directing every step. In one case it guessed passwords; in two others it found credentials in a public repository, then used them to enter protected systems. Gemini stopped after recognizing the systems were real, and Google said it saw no need for public disclosure because no harm occurred.