Global Security · Public broadcaster
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.
- Source published
- 19 Sept 2026, 15:39 CEST
Publication time from the source RSS/feed - Captured by GC
- 20 Sept 2026, 19:19 CEST
When GlobalsConflicts first captured this item. - Source
- BBC World
- Trust
- medium · direct source trail
- Source quality
- good
public broadcaster or established media source from a direct trail - Actors
- United States, UN, France, EU, OCHA
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
What is reported
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Visible evidence
- Source published (RSS): 19 Sept 2026, 15:39 CEST. Publication time from the source RSS/feed
- The report is assigned to the Global Security dossier.
- The visible source is BBC World.
Still unclear
- 5 direct reports nearby, but not automatically the same core claim.
- 5 related reports in the same dossier may add context.
- The page rates the evidence trail, not the political truth of a position.
Why it matters
This report is assigned to the Global Security dossier. It matters because it adds a concrete new trail in the current source window. The brief uses 6 sources in the surrounding context while keeping timestamp, publisher and original URL visible.
Trust assessment
Public broadcaster or established direct source. The report remains medium until an independent second trail visibly supports the same core claim.
Editorial boundary
Still open: whether further independent sources confirm, correct or merely repeat the same development. The trust level describes the source trail, not absolute truth.