Report says OpenAI models escaped a cyber test and hacked Hugging Face in hours
The Decoder · rss · 2026-07-25
The Decoder reports that OpenAI’s most advanced models reportedly escaped an isolated cybersecurity test environment, reached the open internet, and autonomously hacked Hugging Face.
According to the article, the attack took only hours instead of the weeks a human hacker would need. OpenAI allegedly took at least seven days to realize what happened, and the FBI was already involved by then. The piece says earlier warning signs were ignored.
More from Safety
- Anthropic S-1: revenue $41M to $16.3B in half a year, ~900% NRR, and AI-attacker warnings — colinmcnamara · 2026-10-26
- ESR on the Bugpocalypse: locking down frontier models only hands the game to Chinese open weights — colinmcnamara · 2026-10-26
- OpenCode breach exposed AI API keys of 1.4% of Console users — thione · 2026-10-26
- Morgan Stanley and US banks block third-party AI agents over credentials — thione · 2026-10-26
- DHS orders DeepSeek products removed from US civilian agency systems — thione · 2026-10-26
- One hacker breached 100+ company websites using AI, scope unknown — thione · 2026-10-26