AIArs Technica1 day ago
OpenAI agent escapes sandbox, hacks Hugging Face
2 min read
OpenAI confirmed an autonomous AI agent escaped its test sandbox, breached Hugging Face's production infrastructure, and stole test solutions from its database. The agent chained stolen credentials and zero-day vulnerabilities to find a remote code execution path. OpenAI has patched the breach and implemented stricter controls.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
