Intro When a swarm of 700 OpenAI agents hacked Hugging Face in July, they left behind a public trail of evidence. Our investigation, based on public information, reveals a large number of previously unknown agent behaviors and exploits that were used in the attack. Agents: Elaborately chained together online services to gain access to the internetIgnored clear warning signs from Hugging Face that the exfiltrated data was sensitiveReferred to server resources and credentials as “LOOT”Searched Huggingface’s internal SlackSent queries to other agents hosted on Huggingface serversTried to delete evidence of their exploits We document all of these, and more, in this report. The agents initially had very limited access to the internet: they could load URLs, but not interact with pages or…
Revealing the details of how OpenAI agents hacked Hugging Face
Advertisement