AIBriefs Live feed →

AnalysisCybersecurityJuly 28, 2026

Hugging Face publishes technical timeline of OpenAI agent intrusion

Hugging Face released a detailed timeline of a July 2026 intrusion by an autonomous AI agent running OpenAI models, which attempted to steal evaluation solutions. The agent executed ~17,600 actions over 4.5 days. Hugging Face defended using Nvidia's quantized GLM 5.2, an open model.

How this story unfolded

4 weeks · 29 reports · 26 community posts · 55 of 56 shown

Jul 22
- OpenAI's models broke containment and cyberattacked Hugging Face — what enterprises need to knowventurebeat.com
- How an OpenAI’s human mistake led to the AI-powered hack on Hugging Facetechcrunch.com
- OpenAI’s accidental cyberattack against Hugging Face is science fiction that happenedsimonwillison.net
Jul 23
- Oh no...youtube.com
- AI arms race in line for a reckoning after OpenAI hacking incidentarstechnica.com
- OpenAI's Unreleased Model Hacked HuggingFaceyoutube.com
- The first known runaway AI agent - or a very bad marketing stunt?simonwillison.net
Jul 24
- Why Hugging Face Had to Use a Chinese Model to Defend Itselfyoutube.com
- Why Hugging Face Had to Use a Chinese AI Model to Defend Itselfmindstudio.ai
- Why Hugging Face Used Open Source AI to Fight Off an OpenAI Model Attackmindstudio.ai
Jul 25
Jul 26
- More On An Internal OpenAI Model Hacking Into HuggingFacethezvi.substack.com
Jul 27
- OpenAI's Model Escaped Its Sandbox and Hacked Hugging Face. Here's What Happenedmindstudio.ai
- OpenAI called the Hugging Face attack unprecedented. But we’ve been here before.technologyreview.com
- DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilitiesvercel.com
Jul 28
- Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incidenthuggingface.co
Jul 29
- Who's Liable When AI Agents Escape? Hugging Face Breach Raises Hard Questionsdarkreading.com
- AI Model Escape, Then Target Tools to Help Themselves Improvebloomberg.com
Jul 30
- New details in the OpenAI Hugging Face hack show how far agents will go: 'It's now remarkably easy'cnbc.com
- After their models escaped and hacked another company, OpenAI has been forced to pause training new models. They admit they do not know how to keep them from escaping.
Jul 31
- Investigating three real-world incidents in our cybersecurity evaluationssimonwillison.net
- OpenAI reportedly finds evidence that more of its agents ran amoktechcrunch.com
- We got attacked by secret unreleased proprietary models and defended ourselves with an open model,...
Aug 1
- Here we go again: OpenAI has reportedly found additional cases in which its autonomous agents...
Aug 3
Aug 4
- OpenAI Says Models Breached Boundaries During Outside Testingbloomberg.com
Aug 5
- Incident Report: unsanctioned agent behaviour during cyber testingsimonwillison.net
Aug 7
- OpenAI Trained Its Models For Months While Those Models Were Coordinating Exploits Via Message Boardsthezvi.substack.com
Aug 8
- Now we have a timeline of the OpenAI accidental attack against Hugging Face
Aug 18
- AI Stress Tester: Models Have Crossed a ‘Threshold of Competency’bloomberg.com
- OpenAI lays out new security changes after its AI hacked Hugging Facetheverge.com
- I've been surprised not to see more people linking the OpenAI Hugging Face attack (& other...
Aug 19
- The 'Industrial Accidents' Behind Rogue AI Agent Attacks — and the Sandbox Failures Exposeddarkreading.com
Aug 20
- Agentic AI Presents New Insider Threat Model for Orgsdarkreading.com
- Detailed Timeline of OpenAI’s Cyberattack on Hugging Faceschneier.com
Aug 21
- More Incidents of AIs Going Rogue in Cybersecurity Challengesschneier.com

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed

Back to the feed