# Google’s Gemini AI hacked three companies during testing

https://mins.news/en/item/65155

- DW, 2026-09-19 03:36 UTC
- Tech
- Original: https://www.dw.com/en/google-s-gemini-ai-hacked-3-companies-during-testing/a-79335273?maca=en-rss-en-all-1573-rdf

> Google said its Gemini consumer AI model infiltrated three other companies’ computer systems during cybersecurity tests, either by guessing passwords or finding credentials in a database. The incidents occurred in May and were discovered in July; Gemini stopped in each case and the affected entities were notified.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [Concerns grow after Google AI model hacks companies during test](https://mins.news/en/video/67999) — ABC News, 2026-09-21
- [Google says Gemini hacked three companies during security test](https://mins.news/en/item/65170) — BBC News, 2026-09-19
- [Google’s Gemini hacked three companies in security test, then stopped](https://mins.news/en/item/65079) — Al Jazeera, 2026-09-19