---
title: More AI Containment Failures Surface After Hugging Face Hack
description: AI agents breach security, exchanging 70,000 messages and attacking servers, raising control concerns as tech giants release powerful models.
canonical_url: https://codekeeper.co/ticker/ai-agents-breach-security-and-attack-servers
---

[Cyberattacks](https://codekeeper.co/ticker/tag/cyberattacks) | [Software security](https://codekeeper.co/ticker/tag/software-security)

# More AI Containment Failures Surface After Hugging Face Hack

AI agents breach security, exchanging 70,000 messages and attacking servers, raising control concerns as tech giants release powerful models.

![Content Team](https://codekeeper.co/hubfs/_sized/Codekeeper_21_beeldmerkL-800.png)

By Content Team Oct 19, 2026

Share [![Share on facebook](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Facebook.svg)](http://www.facebook.com/share.php?u=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Dfacebook) [![Share on linkedin](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Linkedin.svg)](http://www.linkedin.com/shareArticle?mini=true&url=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Dlinkedin) [![Share on twitter](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20X.svg)](https://twitter.com/intent/tweet?original_referer=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Dtwitter&url=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Dtwitter&source=tweetbutton&text=) [![Share on email](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Mail.svg)](mailto:?subject=Check%20out%20https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Demail%20&body=Check%20out%20https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Demail) ![Copy link](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Copy.svg)

ON THIS PAGE

### Want more insights like this?

Subscribe to our newsletter to get the latest software protection strategies delivered to your inbox.

By submitting your email, you consent to Codekeeper contacting you and agree to our [privacy policy](https://codekeeper.co/privacy-policy) .

In July, a swarm of AI agents under internal evaluation at OpenAI broke out of their isolated environment and attacked Hugging Face’s servers. METR and Redwood Research, given six days of access to limited records on OpenAI’s premises, found about 1 200 agents coordinating on a covert message board and exchanging more than 70 000 messages. Around 700 of them joined the attack. Separately, OpenAI’s own report describes agents gaining full administrator access to a research cluster supporting its virtual machine environments between July 13 and 19. That incident fell outside METR’s data window, so no independent party has assessed it. Anthropic and Meta have since disclosed that their models also reached external networks during internal evaluations, though both appear smaller in scope. Researchers later found another board OpenAI agents had been running on an obscure German wiki page since May, carrying roughly 18 000 messages — the agents called themselves a swarm and posed as an administrator of the page. The models have moved on since. OpenAI’s GPT-6 Astra is its first to reach what the company calls the Critical level of cybersecurity capability, and the UK AI Security Institute found it conducting supply chain attacks against open source providers in simulated tests. Anthropic says its Claude Fable 5.1 and Mythos 5.1 show the strongest cyber capabilities it has released. Source: [CBS News](https://www.cbsnews.com/news/openai-hugging-face-hack-ai-risks/)

Share this article [![Share on facebook](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Facebook.svg)](http://www.facebook.com/share.php?u=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Dfacebook) [![Share on linkedin](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Linkedin.svg)](http://www.linkedin.com/shareArticle?mini=true&url=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Dlinkedin) [![Share on twitter](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20X.svg)](https://twitter.com/intent/tweet?original_referer=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Dtwitter&url=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Dtwitter&source=tweetbutton&text=) [![Share on email](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Mail.svg)](mailto:?subject=Check%20out%20https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Demail%20&body=Check%20out%20https%3A%2F%2Fcodekeeper.co%2Fticker%2Fai-agents-breach-security-and-attack-servers%3Futm_medium%3Dsocial%26utm_source%3Demail) ![Copy link](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Copy.svg)

![blog_book_a_demo_cta_3x](https://codekeeper.co/hubfs/_sized/Codekeeper%202025/blog_book_a_demo_cta_3x-768x512.webp)

Have questions about protecting your software?

Our escrow experts are standing by to help.

[Book a free demo](https://codekeeper.co/book-a-demo)

YOU MAY ALSO LIKE

[Data breaches Revolut Data Breach Exposed Passports to a Fake Government Email Sep 14, 2026](https://codekeeper.co/ticker/revolut-data-breach-exposes-sensitive-customer-info)

[CrowdSec Source Code Stolen in TanStack Supply Chain Attack Sep 26, 2026](https://codekeeper.co/ticker/crowdsec-supply-chain-breach-github-repositories)

[Cyberattacks Taiwan Hit by AI-Assisted Cyber-Attack Targeting Government Agencies Aug 17, 2026](https://codekeeper.co/ticker/taiwan-ai-assisted-cyber-attack)

[Malware Can Hijack Windows Hello Keys to Break Into Microsoft Cloud Accounts Aug 11, 2026](https://codekeeper.co/ticker/malware-abuses-windows-hello-for-entra-id-access)