The OpenAI models that hacked the startup Hugging Face this month also gained access to a customer account on the cloud platform Modal and used it to launch attacks, underscoring the broad scope of the incident. The Modal customer set up a publicly accessible interface that allowed anyone on the internet to use their sandbox to run code, Bubna said. Hugging Face said in an earlier blog post that the OpenAI system “penetrated” an insecure sandbox hosted on a third-party provider’s infrastructure, without naming the company. The San Francisco-based startup added that the models that breached Hugging Face also used “code paste websites, request capture services, screenshot services, and other web utilities” in its exploits. Reuters reported earlier on Tuesday that a Modal customer had been compromised.