1
VulnHunter: Agentic AI Security Tool
基于 Claude 的自主 AI 安全工具，实时检测漏洞并提供智能防护，让代码安全更高效。
Article URL: https://github.com/capitalone/VulnHunter Comments URL: https://news.ycombinator.com/item?id=48942583 Points: 1 # Comments: 0
2
Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation
本地小模型也能干安全活了，用可验证后训练搞定Linux权限提升，告别闭源云依赖。
arXiv:2603.17673v2 Announce Type: replace-cross Abstract: LLM agents are becoming increasingly important in the security domain, but leading systems a…
3
Show HN: Nenya – A lightweight, highly secure AI API Gateway/Proxy written in Go
轻量级、高安全的Go语言AI API网关，代理保护你的AI请求安全无忧。
Article URL: https://github.com/gumieri/nenya Comments URL: https://news.ycombinator.com/item?id=48506994 Points: 1 # Comments: 0
4
Show HN: AVP – an agent can't leak a secret it never had
10秒部署的本地代理，防止AI代理泄漏你的凭证，连它自己都记不住秘密。
A process can't leak a secret it never had. Shai-hulud, prompt-injection - you name it. They cannot steal what your agent (or an process) don't have. …
5
How to force AI agents to use an egress proxy
强制AI代理走出口代理，从沙箱环境到网络配置一步到位
Article URL: https://simedw.com/2026/06/05/proxy-agents/ Comments URL: https://news.ycombinator.com/item?id=48411484 Points: 3 # Comments: 1