Gbhackers AI Initiative Helps Fix 55 Vulnerabilities in Open Source Projects
Article Content
- •AI-assisted initiative helped fix 55 vulnerabilities across six open-source projects.
- •Codename MDASH filtered thousands of potential issues down to 99 verified reports.
- •Maintainers retained control over fixes, leading to rapid deployment of patches.
On November 17, GitHub and Microsoft announced a pilot project that utilized AI to assist maintainers in fixing vulnerabilities across six open-source projects. The initiative narrowed down thousands of potential issues to 99 verified reports, with 55 vulnerabilities successfully fixed as of November 15. The AI system, Codename MDASH, employed Microsoft’s MAI Cyber model to suggest fixes, while a triage agent filtered out duplicates and assessed validity. Maintainers retained control over which issues to address and when to release patches. Projects involved included AutoGPT, Caddy, Express, FastMCP, ImageMagick, and Netty. The pilot aimed to reduce the workload on maintainers by providing actionable fixes rather than just findings. The results showed that maintainers were able to implement fixes quickly, with some patches deployed within a week.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (5)
Following this threat?
Track Microsoft in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Common questions
Which projects were involved in the AI initiative?
How many vulnerabilities were fixed?
What was the role of Codename MDASH?
Continue Reading
Lazarus Group Targets 30 South Korean Servers Using PHP Vulnerabilities North Korea-linked Lazarus Group has targeted 30 servers in South Korea as part of a larger cyber operation involving 581 servers across 10 countries. The attacks exploit two critical remote code execution vulnerabilities in PHP (CVE-2026-109618 and CVE-2026-109619), allowing unauthorized server command execution. The…