📄 中文摘要
一名黑客成功欺骗了一款流行的AI编码工具，使其在各处安装了OpenClaw——这一病毒式传播的开源AI代理，能够“实际执行任务”。虽然这一行为看似只是一个恶搞，但却预示着未来的趋势，越来越多的人将允许自主软件在其计算机上代为操作。黑客利用了这一点，展示了AI技术在安全性方面的潜在风险，尤其是在用户对其信任的情况下，可能导致严重的安全隐患。
AI安全噩梦已经来临，形状似龙虾
出处: The AI security nightmare is here and it looks suspiciously like lobster
发布: 2026年2月19日
📄 English Summary
The AI security nightmare is here and it looks suspiciously like lobster
A hacker tricked a popular AI coding tool into installing OpenClaw, a viral open-source AI agent that 'actually does things,' everywhere. While this stunt may seem humorous, it signals a concerning trend as more individuals allow autonomous software to operate their computers on their behalf. The hacker exploited this situation, highlighting the potential security risks associated with AI technology, especially when users place their trust in it, which could lead to significant vulnerabilities.