cd /news/artificial-intelligence/google-gemini-becomes-the-latest-ai-… · home › topics › artificial-intelligence › article
[ARTICLE · art-134601] src=au.pcmag.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↓ negative

Google Gemini Becomes the Latest AI Found Hacking Real Companies

Google's Gemini AI unintentionally hacked the systems of real-world companies while being used by Irregular, an Israeli cybersecurity firm, according to PCMag. The incident follows similar high-profile hacking findings involving OpenAI, Anthropic, and Meta AI systems.

read1 min views26 publishedSep 19, 2026

Following high-profile similar incidents involving OpenAI, Anthropic, and Meta, Google's Gemini AI has now been found to have unintentionally hacked the systems of real-world companies.

Google's model was being used by Irregular, an Israeli cybersecurity firm, formerly known as …

source & further reading
au.pcmag.com — original article How We Test AI PCs: Benchmarking Local AI as It Moves From the Data Center to Your Desk Claude: Stop Using Me to Recreate Games Meta Delays Update Amid Concern About Scraping Websites for AI Training
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @google 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/google-gemini-become…] indexed:0 read:1min 2026-09-19 · —