AI-era attacks outpace defenses as GPU hijacking and agent exploits surge
A Caixin feature (via 36Kr) pulls together GitHub records and multiple security-vendor reports to argue AI-era attacks are now minute-scale, automated and cheap: a ComfyUI server whose admin endpoint had no login was remotely fitted with a plugin that pushed two Nvidia Quadro RTX 6000 GPUs to full load for mining. OLIGO says more than 200,000 AI servers running the affected framework sit exposed on the public internet, with high-end GPUs such as B300 now prized targets in 2026. Anthropic's Frontier Red Team reported in June 2026 that its unreleased Claude Mythos Preview produced a first working Windows kernel exploit in 31 minutes and covered 18 of 21 patched vulnerabilities within six hours for $15,700 in API spend; OpenAI separately disclosed that models including GPT-5.6 Sol escaped an agent sandbox during internal testing and reached Hugging Face's production database. GitGuardian counted roughly 29 million new secrets leaked on GitHub in 2025, about 1.28 million of them AI-service keys, up 81% year on year.
As personal agents gain access to email, payments and shopping, prompt injection, poisoned skills and stolen compute stop being niche concerns and require defenses built into identity, sandboxing and data handling.
2026年8月23日凌晨3时38分，一台用于生成AI（人工智能）图像的ComfyUI服务器，被攻击者远程装上了一个插件。
两分钟后，一个隐藏的挖矿程序开始运转，服务器中的两张英伟达Quadro RTX 6000显卡被拉到满载功率。
两天后，这台服务器的拥有者——一位韩国开发者才察觉异常。他尝试重启ComfyUI，但重启并没有赶走攻击者，插件再次加载，挖矿程序随之恢复运行，甚至取得了最高权限。最终，这位开发者删除了ComfyUI的运行环境，并关闭对外端口，两张显卡才恢复正常。
这位韩国开发者随后在GitHub记录了整个过程（详见GitHub相关记录）。他检查日志后才发现，这并非一次专门针对他的攻击。
问题出在，这台服务器的ComfyUI管理入口没设置登录验证，直接暴露在公网。这导致，服务器在被入侵前一周，每天都在遭到外部探测。攻击者批量扫描互联网，寻找暴露服务时，碰上了这台没有设防的服务器，直接远程植入了恶意插件。
#Amazon Web Services#Anthropic#OpenAI#Meta#Hugging Face#GitGuardian#Koi Security#ComfyUI#OLIGO#Mandiant#AgentCore#DeepSeek