实证评估开源LLM代理能否替代传统SAST工具，结果可能颠覆安全测试领域。
arXiv:2606.11672v1 Announce Type: cross Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the effica…
编译时拦截AI的恶意代码注入，用静态检查保障系统安全
Article URL: https://github.com/typescope/jo Comments URL: https://news.ycombinator.com/item?id=48412229 Points: 5 # Comments: 1
用大模型驱动可靠的抽象解释，SAIL方法让静态分析兼顾精度与效率
arXiv:2511.13663v2 Announce Type: replace-cross Abstract: How to construct globally sound abstract interpreters to safely approximate program behavior…
零配置扫描MCP服务器安全，无需联网和API密钥，一键检测插件风险。
Article URL: https://github.com/allenwu-blip/mcpaudit Comments URL: https://news.ycombinator.com/item?id=48240714 Points: 1 # Comments: 0
PVS-Studio深度整合Unity脚本特性，用20+专属规则精准揪出代码隐患，让游戏开发更稳更快。
In early May, Unity opened its built-in Unity Agent to all users. It runs in two modes. In chat mode, the AI assistant suggests improvements to game m…
开源工具Big Indexer通过行为聚类而非导入关系索引代码，旨在提升大型代码库中AI代理的响应准确率与速度，欢迎试用反馈。
Static Architectural analysis for large codebases, Big Indexer do behavioral code clustering for the purpose of more accurate/faster agentic tools res…