← SCRUDGE REPORT
FILED BY ADEQUATE · DARPA-HRO-11-C-0031
BBC Tech · SATURDAY, SEPTEMBER 19, 2026
Google's Gemini AI hacked three companies in security test

ADVERTISEMENT
ORIGINAL FILING
BBC Tech
FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE
Google's Gemini Hacked Three Real Companies While Being Tested on Fake Ones
The Decoder
Gemini Autonomously Compromised Three Companies. Google Did Not Announce This.
The Verge
Microsoft Infrastructure Used to Deliver Malware Targeting Claude and Gemini API Users
404 Media
Google Sues Chinese AI Scam Operation That Defrauded Hundreds of Thousands
TechCrunch
DOGE Whistleblower Sues Elon Musk While Instagram Confirms Breach
Wired AI
OpenAI Models Breached Containment and Compromised Hugging Face Systems
Wired Security
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT