Google’s Gemini Hacked Three Companies in May, and It’s Only Admitting That Now
Google’s Gemini has finally joined the ranks of AI rogue agents. The Wall Street Journal reported on Friday that Google has confirmed that a Gemini instance was able to leave its sandbox and attack other companies during a security test back in May. The company running the test was frontier AI security firm Irregular—which the Journal noted just so happens to have been involved in similar breakouts at OpenAI, Anthropic, and Meta.
- ▪Google’s Gemini has finally joined the ranks of AI rogue agents.
- ▪The Wall Street Journal reported on Friday that Google has confirmed that a Gemini instance was able to leave its sandbox and attack other companies during a security test back in May.
- ▪The company running the test was frontier AI security firm Irregular—which the Journal noted just so happens to have been involved in similar breakouts at OpenAI, Anthropic, and Meta.
8 outlets in our directory ran this story, first to last over 4 hours. Coverage spans 2 points on the political spectrum — 2 lean left, 5 centre.
- ▪ Gemini hacked three companies in first known breakout by Google's AI — Hacker News (AI / LLM)
- ▪ Google says its Gemini AI model hacked three other companies - The Guardian — Google News
- ▪ Google says its Gemini AI model hacked three other companies — The Guardian — Tech
- ▪ Gemini AI Hacked Three Companies in a Testing Breakout, Google Says — NYT — Technology
- ▪ Google’s Gemini Model Hacks Companies During Test — The Information
- ▪ Gemini hacked three companies in May during a test by Irregular; Google says the model stopped after determining it had accessed real companies' systems (Wall Street Journal) — Techmeme
- ▪ Gemini Hacked Three Companies in First Known Breakout by Google's AI — The Wall Street Journal
Gizmodo files mainly under tech. We currently carry 1,148 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Gizmodo |
| Canonical URL | https://gizmodo.com/googles-gemini-hacked-three-companies-in-may-and-its-only-admitting-that-now-2000814420 |
| Publication time | Sat, 19 Sep 2026 02:01:55 +0000 |
| Retrieval time | 2026-09-19T02:03:46.239Z |
| Last seen | 2026-09-19T02:03:46.239Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | WpLjIklIrJQf · 9 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Google’s Gemini has finally joined the ranks of AI rogue agents. The Wall Street Journal reported on Friday that Google has confirmed that a Gemini instance was able to leave its sandbox and attack other companies during a security test back in May. The company running the test was frontier AI security firm Irregular—which the Journal noted just so happens to have been involved in similar breakouts at OpenAI, Anthropic, and Meta. The common thread between all of the incidents, according to the New York Times, is that AI models obtained unauthorized internet access during Irregular’s tests. According to the Journal, Irregular deployed Gemini in a capture-the-flag exercise involving a simulated infrastructure environment for a fictional company.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Gizmodo.
Discussion
0 commentsMore from Gizmodo
