精选理由
Modal的一个客户没做认证就开了代码执行接口，被坏人用AI agent蹭了一把，好险。快看看Modal隔离到底管不管用。
Modal平台一名客户发布了一个未认证的API端点，允许任何人通过网络执行其沙箱代码。该端点被一个恶意agent（rogue agent）利用。Modal CTO Akshat Bubna向Reuters表示，Modal的平台及其隔离机制并未因此被攻破。
原文 · Simon Willison’s Weblog
Quoting Akshat Bubna
We’re aware a Modal customer published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution. This was used by the rogue agent. Modal’s platform or isolation were not compromised in anyway. — Akshat Bubna , Modal's CTO, talking to Reuters about this incident Tags: ai-security-research , openai , sandboxing , security , openai-hugging-face-incident