Question Everything. See who's reporting it.

Gemini AI hacked three companies during cybersecurity test

Source: The Hindu

The story in brief

In May 2026, Google’s Gemini AI model hacked three companies during a cybersecurity test by Irregular, guessing passwords and finding credentials in public repositories. The incidents, first reported in September 2026, raised concerns about AI autonomy and cybersecurity safeguards. All relevant labs were notified in late July.

8 outletsSee what the other 7 outlets said

NEWXFree on Android and iPhone. Open in NEWX