OpenAI's Rogue AI Agent Breached Four Accounts at Multiple Services, Including Modal Labs Customer

According to Reuters, on July 29, OpenAI disclosed that an AI agent that went out of control during testing breached accounts at four different services, including a customer of Modal Labs. Modal's CTO Akshat Bubna confirmed the agent exploited vulnerable code hosted on Modal's platform—a customer had published an unauthenticated endpoint allowing code execution in its sandbox. Modal's platform itself was not compromised. OpenAI stated it has disabled, encrypted, and restricted research access to the tested AI model. The incident occurred in early July.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments