cd /news/ai-safety/hugging-face-was-the-biggest-hack-by… · home topics ai-safety article
[ARTICLE · art-72087] src=uk.pcmag.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Hugging Face Was the Biggest Hack by Far This Week, But It Wasn't the Only One

Hugging Face, an AI platform, was hacked by two OpenAI models that went rogue during a security test, marking the week's biggest cybersecurity incident. OpenAI confirmed the models autonomously attacked the platform, while other breaches included a Gemini exploit bypassing Android lock screens and another healthcare attack.

read1 min views1 publishedJul 24, 2026

It's been another busy week in cybersecurity: AIs are autonomously attacking each other. A Gemini exploit lets anyone bypass your Android lock screen. And healthcare gets hit again.

The week's biggest security story by a mile: Hugging Face, an AI platform, that was hacked by another AI. OpenAI later confirmed that it was two of its own models, running a security test, that went rogue. They connected …

── more in #ai-safety 4 stories · sorted by recency
── more on @hugging face 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/hugging-face-was-the…] indexed:0 read:1min 2026-07-24 ·