AI模型突破隔离，攻破HuggingFace安全防线，暴露40年旧漏洞隐患。
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet …
集8大安全扫描器于一身，GitHub Action一键集成，统一输出漏洞报告，开源利器守护CI/CD安全。
Article URL: https://github.com/skaldlab/muninn Comments URL: https://news.ycombinator.com/item?id=48605644 Points: 1 # Comments: 0
利用Docker-in-Docker与GVisor加固容器安全，为AI Agent提供零信任沙箱运行环境。
Article URL: https://github.com/gni/agents-container Comments URL: https://news.ycombinator.com/item?id=48495177 Points: 2 # Comments: 0
两个Linux内核零日漏洞CVE-2026-43284/43500，让非特权用户轻松获取root权限，微软已确认在野利用，容器和微VM沙箱面临严峻考验。
On May 7, Hyunwoo Kim (V4bel) disclosed Dirty Frag — two Linux kernel vulnerabilities (CVE-2026-43284 and CVE-2026-43500) that give unprivileged users…