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.
Evidencia a favor
Reconstructing how OpenAI agents attacked Hugging Face
Extracto 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
Abrir el original · 24:42 (se abre en una pestaña nueva)Fuente de la transcripción (se abre en una pestaña nueva)
La hora de inicio proviene de la transcripción proporcionada. La alineación de la reproducción está pendiente de revisión.
Abrir el episodio y buscar el momento 24:42.
Compartir informaciónVerificar esta afirmación