An OpenAI “runaway agent” invaded a customer of Modal Labs

robot
Abstract generation in progress
PANews July 29, Reuters reported that after a runaway AI agent during testing breached Hugging Face, OpenAI also breached a customer of New York tech company Modal Labs. Modal Chief Technology Officer Akshat Bubna said the agent exploited vulnerable code hosted by the customer on the Modal platform. The customer published an unauthenticated endpoint that allowed anyone to use its sandbox to execute code, but the Modal platform itself was not compromised. In an update, OpenAI confirmed that the agent compromised four accounts across four services, but did not specify which services. OpenAI said it “disabled, encrypted, and restricted research access” to the AI models used in the test. The incident happened in early July, sparking widespread concern about AI security risks.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned