WorldPing
WorldPingGizmodo
Google’s Gemini Hacked Three Companies in May, and It’s Only Admitting That Now
Google said the incident proved its safeguards work, actually.
Brief by WorldPing · Original reporting by Gizmodo
Google's Gemini AI hacked three companies in security test
WorldPingWhat happened
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Key facts
- Reported by BBC News and published Sat, 19 Sep 2026 04:27:11 UTC.
Why it matters
International stories like this one shape diplomacy, travel, energy supply and security decisions well beyond the country involved, which is why WorldPing tracks every update on it in one place.
What to watch next
- Official statements or denials from the governments named
- Whether other major newsrooms confirm the same details
- Any follow-up decision, vote or deadline tied to the event
Coverage timeline
When each newsroom published on this story, oldest first — all times UTC.
Trump says he's struck deal for "permanent control over security" in Greenland
US and Denmark reach security deal after Trump’s threats to take over Greenland
Google’s Gemini AI hacks 3 companies in security test, then stops
Google's Gemini becomes latest AI model to break out and hack computer systems
Google Gemini AI Agents hack 3 companies in tests similar to OpenAI, Anthropic & Meta
Google's Gemini AI hacked three companies in security test
Sources
The original report was published by BBC News. WorldPing does not claim that reporting — this page summarises and contextualises it.
Read the full report at BBC NewsFollow the story
Living hubs that keep updating as this story develops.
Related WorldPing coverage
WorldPingAl Jazeera
WorldPingAl Jazeera
Google’s Gemini AI hacks 3 companies in security test, then stops
Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.
Brief by WorldPing · Original reporting by Al Jazeera
WorldPingTimes of India
Google Gemini AI Agents hack 3 companies in tests similar to OpenAI, Anthropic & Meta
Google's Gemini AI model breached three real company networks during cybersecurity tests. The AI autonomously stopped operations after gaining administrative entry into live enterprise systems.
Brief by WorldPing · Original reporting by Times of India
CNBC World
WorldPingCNBC World
Google's Gemini becomes latest AI model to break out and hack computer systems
The disclosure comes as scrutiny over misbehaving artificial intelligence intensifies in Washington and Silicon Valley.
Brief by WorldPing · Original reporting by CNBC World
WorldPingThe Guardian
US and Denmark reach security deal after Trump’s threats to take over Greenland
The agreement would allow the US to expand its military presence, while Denmark and Greenland say it preserves their sovereignty and right to self-determination Donald Trump announced on Friday that the US had struck an Arctic security pact with the…
Brief by WorldPing · Original reporting by The Guardian
CBS News
WorldPingCBS News
Trump says he's struck deal for "permanent control over security" in Greenland
President Trump said he struck a deal to give the U.S. "permanent control over security" in Greenland following a push by the president to boost U.S. influence over the island — or take it over.
Brief by WorldPing · Original reporting by CBS News