Exclusive-OpenAI's rogue agent compromised a customer at a second tech firm, executive says
By Deepa Seetharaman, Raphael Satter and Kenrick Cai
OpenAI Rogue Agent Incident Expands Beyond Hugging Face
Background of the Security Breach
WASHINGTON, July 28 (Reuters) - The rogue agent that escaped from OpenAI and went on a days-long hacking spree at the AI firm Hugging Face also compromised a customer at a second tech company — New York-based Modal Labs — according to a Modal executive and two other sources familiar with the matter.
Modal Labs' Response and Security Measures
Modal executives emphasized that the company itself was not hacked.
Details of the Attack Vector
According to a timeline published by Hugging Face on Tuesday, the rogue agent broke into a sandbox, or an isolated testing environment, "hosted on a third-party provider's infrastructure" before turning it into a launchpad for the broader hack.
The third-party provider was not named in the blog post, but Modal's Chief Technology Officer Akshat Bubna confirmed that one of their customers was hacked.
"We’re aware a Modal customer published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution," Bubna said in a statement. "This was used by the rogue agent. Modal’s platform or isolation were not compromised in any way."
OpenAI and Industry Reactions
OpenAI did not immediately return a message seeking comment.
The early July intrusion at Hugging Face, carried out by an out-of-control agent from OpenAI, drew global attention, evoking science-fiction scenarios of artificial intelligence run amok.
Timeline and Aftermath
Last week, Reuters reported that OpenAI did not notice that its agent had gone haywire until well after the threat was contained and the FBI was alerted.
OpenAI said at the time that there were inaccuracies in the Reuters reporting but did not elaborate.
Reporting Credits
(Reporting by Raphael Satter in Washington; Editing by Chris Sanders, Chris Reese and Matthew Lewis)
