AnalysisCybersecurityJuly 28, 2026
Hugging Face publishes technical timeline of autonomous AI agent intrusion
An autonomous agent running OpenAI's ExploitGym benchmark performed ~17,600 actions against Hugging Face infrastructure over 4.5 days in July 2026. The intrusion, which aimed to steal evaluation solutions, was contained using the open-weights GLM-5 model.
15 sources
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incidenthuggingface.co
OpenAI and Hugging Face partner to address security incident during model evaluationopenai.com
if anyone wonders how a root cause analysis should look like and a post incident report this is...x.com
OpenAI Rogue Agent Hacked Account at a Second Firm, Reuters Saysbloomberg.com
Quoting Akshat Bubnasimonwillison.net
JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breachthehackernews.com
More On An Internal OpenAI Model Hacking Into HuggingFacethezvi.substack.com
The Hugging Face Incidentastralcodexten.com
OpenAI's Hugging Face hack triggers 'AI Kill Switch' bill in Congresscnbc.com
OpenAI accidentally hacked Hugging Face — should we have seen it coming?epochai.substack.com
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Tool installs configurations for Claude Code, Codex CLI, Gemini CLI, and Cursor
- Baidu's Apollo Go begins robotaxi road tests in London
- OpenAI releases GPT Transcribe speech-to-text model
- SKT and KRAFTON release A.X-K2 model
- AI-2027 and AI-2040 researcher calls 'Pacing the Frontier' letter a success