GitHub Codename MDASH 试点:把海量 AI 发现压缩成 99 份带修复方案的报告
Maintainers don’t need more AI bug reports. They need fixes.
GitHub 和 Microsoft 把几千条 AI 漏洞线索筛成 99 份带修复建议的私密报告,开源维护者已修掉一半以上。它没有走「AI 报告海」的老路,而是先验证再交付。如果你维护开源项目、经常被低质量 issue 淹没,这份试点经验直接可借鉴。
GitHub 与 Microsoft 联合开展 Codename MDASH 试点,面向六个广泛使用的开源项目,将数千条原始 AI 安全发现筛减为 99 份经过核实的私密报告,每份都附带建议修复方案。
流程的核心不是让 AI 直接产出漏洞清单,而是加入人工与自动化核验环节,剔除误报后只把可执行、可复现的问题交给维护者。截至目前,维护者已经修复了其中超过一半的报告。
这一试点回应了开源维护者长期抱怨的问题:AI 生成的 bug 报告数量激增但质量低下,反而占用维护时间。MDASH 的做法把「更多报告」换成「更少但带修复的报告」,为开源社区处理 AI 时代的安全披露提供了一种可参考的协作模式。
Maintainers don’t need more AI bug reports. They need fixes.
In the Codename MDASH pilot, GitHub and Microsoft turned thousands of raw AI findings into 99 checked, private reports with suggested fixes for six widely used open source projects. Maintainers have already fixed more than half. The post Maintainers don’t need more AI bug reports. They need fixes. appeared first on The GitHub Blog .
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include GitHub, Microsoft, open source, AI safety.
Primary source verification: published directly by GitHub Blog with first-party authority.