Breaking news, curated around the clock
Home /Tech

Google's Gemini AI hacked three companies in security test

Tech | 2026-09-19 at 04:27 UTC | Source: www.bbc.co.uk
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Read Full Article →
← More Tech news
Related Articles
2026-11-04 · 10:10
Tell HN: Gemini trains on chat history, even for subscribers (personal accounts)
Google's Gemini AI service uses saved chat history from paid subscribers to train its models, with no opt-out…
2026-11-03 · 16:45
Gitbook Breached
GitBook experienced a security breach on November 2 when attackers used AI agents to gain unauthorized access…
2026-11-03 · 18:57
GitBook AI Attack Exposes API Secrets, Triggers Urgent Security Response
GitBook has urged customers to rotate API keys and third-party credentials after attackers used AI agents to…
2026-11-03 · 17:56
CrowdStrike to shell out nearly $500M for 2 AI security startups as the market for securing agents takes off
CrowdStrike said it will buy Fiddler AI, which makes AI agent observability software, and Dreadnode, which…
2026-11-03 · 15:41
Are the Fridges Ok?
Supermarket refrigeration systems remain vulnerable to cyberattacks, with internet-exposed Danfoss controllers…