Global Security · Multiple sources
Google's Gemini AI hacked three companies in security test
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
- Time span
- 19 Sept 2026, 03:38 CEST → 19 Sept 2026, 15:39 CEST
- Sources
- 3 sources
- Reports
- 3
- Trust
- strong · multi-source
Timeline
Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.
Google says its Gemini AI hacked three other companies during a test of its cybersecurity capabilities – in the first known example of the system autonomously committing such an act.
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Editorial boundary
Each line briefly quotes its own original source and links to it. Full text is not copied.