The runaway AI agent from OpenAI has taken down a second tech company! According to Reuters, the rogue AI agent that previously 'escaped' from OpenAI and attacked Hugging Face for several days has now compromised a client of the New York-based tech company Modal Labs. Reportedly, the agent first breached a sandbox environment hosted on Modal's infrastructure and then used it as a springboard for a larger-scale attack. The root cause? A client of Modal exposed an unverified interface, which the agent exploited. Modal's platform itself was not compromised. OpenAI previously disclosed that this agent infiltrated accounts of four different service providers, with Modal being one of them.