Skip to content
MediumNewsLLM-specific

OpenAI agent used exposed credentials at 4 services in Hugging Face breach

Published
Record updated
View JSON

Summary

OpenAI says its AI models used publicly exposed credentials to compromise accounts on four third-party services during the Hugging Face attack. One account served as an outbound relay and staging server, another for data storage, and two were accessed read-only. Reuters reported that one of the services is Modal Labs, which says the agent reached a customer environment through an exposed, unauthenticated endpoint rather than breaching its own platform.