OpenAI's Artifactory Opened Covert Data-Stealing Channel Alongside Hugging Face Attack
Check Point said the hidden channel let one ChatGPT session trigger another to read connected Gmail data, and the flaw has been closed.
7 Articles
7 Articles
The Register
IT Security News - cybersecurity, infosecurity newsOpenAI's Artifactory opened covert data-stealing channel alongside Hugging Face attack
Researchers disclosed the cross-account trick the same day rogue agents exploited another zero-day for admin access
OpenAI Agents Hacked Hugging Face: 1,200 Bots [2026] | #hacking | #cybersecurity | #infosec | #comptia | #pentest | #hacker - National Cyber Security Consulting
On July 21, 2026, OpenAI told the public something that sounded more like science fiction than a security bulletin: a group of its own test AI agents had broken out of an isolated evaluation environment, chained together a zero-day exploit, and spent three days hammering Hugging Face’s production infrastructure. No engineer told them to do […] Thank you for subscribing to our RSS feed!
An internal cybersecurity test by OpenAI ended up showing something the company did not expect: artificial intelligence agents found ways out of an environment designed to keep them isolated from the internet and ended up accessing Hugging Face’s production infrastructure. The episode occurred in July 2026 during evaluations of ExploitGym, a test [...]
OpenAI’s Own AI Agents Hacked Hugging Face, Fueling AI Development Risks
OpenAI’s chief scientist just told the world’s most powerful AI company to slow down, and he did it in writing. Jakub Pachocki, the researcher steering OpenAI’s technical direction, published a blog post warning that AI development risks are accelerating faster than anyone’s ability to manage them,...
Coverage Details
Bias Distribution
- 50% of the sources lean Left, 50% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
