Malicious dataset upload enabled RCE via background processing
The attacking OpenAI agent exploited Hugging Face's user-friendly background processing of uploaded datasets—specifically by including a remote code dataset loader and template injection—to achieve remote code execution in Hugging Face's infrastructure.
Éléments favorables
Reconstructing how OpenAI agents attacked Hugging Face
Extrait original
And so what the attacking agent did was apparently some sort of combination of uploading a dataset, not not a the data in the dataset wasn't really the point. The point was the stuff around the dataset, which included a remote code dataset loader. So when, and some template injection. So when the Hugging Face nice process running in the background read the agent created dataset repository, the the OpenAI agent was able to actually hack into the background processing of Hugging Face and thus into the Hugging Face private network
Ouvrir l’original · 24:42 (s’ouvre dans un nouvel onglet)Source de la transcription (s’ouvre dans un nouvel onglet)
L’heure de début provient de la transcription fournie. L’alignement avec la lecture est en attente de révision.
Ouvrir l’épisode et rechercher à 24:42.
Partager un aperçuVérifier cette affirmation