BLAST RADIUS

Frontier Line and access · Benchmarks evals

Google Disclosed Gemini-Assisted Real Company Hacking

Sep 19, 2026, first seen via TechCrunch AI. Covered by 3 outlets.

Google said threat actors used Gemini in campaigns that accessed systems belonging to real companies.

Read the original at techcrunch.comOpens the publisher's site in a new tab

Also covering this

Google Gemini accesses protected systems of 3 companies, Trump unveils ‘AI Force’foxnews.com, Sep 20Google's Gemini AI carried out cyberattacks, guessed passwordsmsn.com, Sep 19Google says it didn't consider Gemini's hacks worthy of disclosure because Gemini acted "appropriately" and stopped after determining it hacked real companies (Terrence O'Brien/The Verge)theverge.com, Sep 19Google Gemini Becomes the Latest AI Found Hacking Real Companies | PCMagpcmag.com, Sep 19

More in Frontier Line and access

Google Releases Gemini 3.8 Live Voice ModelsSep 15Trump Calls AI Warnings A HoaxSep 14Apple code indicates possible Siri model swappingSep 14OpenAI Begins Staged GPT-6 Astra RolloutSep 14Senate Bill Would Allow Blocking AI ModelsSep 14