How OpenAI’s human mistake led to the AI-powered hack on Hugging Face

TechCrunchby Lorenzo Franceschi-BicchieraiJuly 22, 2026tech

OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to cybersecurity experts, that human mistake is what made the AI-powered attack on Hugging Face possible.

This article was published on TechCrunch (techcrunch.com). Read the full article on the original source:

Read full article on TechCrunch

#negative #AI #Security #cyberattack #cybersecurity #data breach #Hugging Face #OpenAI

How OpenAI’s human mistake led to the AI-powered hack on Hugging Face

More from TechCrunch

I tried out OpenAI’s new AI keypad — which will be fun for some coders and slightly mystifying to everyone else

SpaceX launches new V3 Starlink satellites but suffers another booster failure

Vietnam is looking to restrict social media for kids; here’s a look at growing number of other countries doing the same

Waymo reportedly mulling a breakup with Uber

Volkswagen engineers charged with insider trading tied to Rivian joint venture

Why Cognition bought Poke: AI personality is becoming a competitive advantage

US accuses American of allegedly wiping his phone using a ‘duress’ password during border search

Anduril reportedly in talks to raise funding at $100B valuation, more than 3x last year’s mark