Industry

GitHub 与 Microsoft Security 将 9,791 条 AI 安全发现筛成 99 份可修报告

Maintainers need fixes, not more AI bug reports. With @msftsecurity, we turned 9,791 raw AI securit...

Why we picked it

GitHub 联手微软安全团队干了件开源圈都该看的事:近万条 AI 报告只留 99 条真的,还带修复方案。做开源维护的、写漏洞扫描工具的都能从这套过滤流程里学到东西,博客里有完整方法。

GitHub 与 @msftsecurity 合作推出安全项目 Codename MDASH,处理了 9,791 条原始 AI 生成的安全发现,最终筛选出 99 份经过验证、私下提交的报告,覆盖六个开源项目,且每份报告附带建议修复方案。该项目的核心机制是用自动化管道过滤大量低质量 AI 报告,只把真正可复现、可修复的问题交给维护者,避免开源维护者被海量噪声淹没。维护者已经开始根据这些报告发布修复。这一做法回应了 AI 时代漏洞报告泛滥的痛点:AI 降低了提交报告的成本,但维护者需要的是带修复建议的高质量报告,而非重复的原始发现。

Body

对开源社区而言,Codename MDASH 提供了一种把 AI 生成发现转化为维护者可用产出的工作流范本。对企业和安全研究者来说,其价值在于验证流程设计——从近万条原始发现压缩到 99 条有效报告的过滤比例,说明了纯 AI 产出与人类验证结合的必要性。开发者应关注其博客中公开的方法论细节。

Original · GitHub

Maintainers need fixes, not more AI bug reports. With @msftsecurity, we turned 9,791 raw AI securit...

Maintainers need fixes, not more AI bug reports. With @msftsecurity , we turned 9,791 raw AI security findings into 99 verified, private reports with suggested fixes for six open source projects. And maintainers are already shipping fixes. What we learned from Codename MDASH, a new security project 🔍 github.blog/open-source/ma… 2📊 10 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Industry" 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, open-source security, AI safety, Codename MDASH.

Source attribution: curated from GitHub (@github).