GitHub turned 9,791 AI security findings into 99 verified reports, 55 already fixed
mariorod1 · x · 2026-11-18
- GitHub and Microsoft ran the Codename MDASH pilot to address the flood of AI-generated vulnerability reports overwhelming open source maintainers.
- Pipeline: Microsoft's MAI Cyber model scans six widely used OSS projects and proposes fixes; a GitHub Security Lab triage agent filters duplicates and false positives; only verified, private reports reach maintainers.
- Result: 9,791 raw findings distilled into 99 verified private reports with suggested fixes — 55 already fixed, more than half.
- Takeaway: maintainers need fixes, not more findings; scan responsibly and come with patches. Log4j maintainer Christian Grobmeier: the AI defending open source must outpace the AI attacking it.
More from coding & agent
- Microsoft opens Web IQ to all Azure customers as a search engine for AI agents — JordiRib1 · 2026-11-18
- Train an object detector for $6 by using LLMs as vision interns, says HF's Merve — mervenoyann · 2026-11-18
- Dev rebuilds all of Singapore in 1:1 scale with 100+ Astra Codex threads and 1,000+ subagents — gabrielchua · 2026-11-18
- Coinbase Ventures maps the agentic trading stack: where value accrues when agents trade — davidyin44 · 2026-11-18
- Separate MCP server vs. mounting MCP in FastAPI: does the extra hop matter? — DetectiveNew8385 · 2026-11-18
- Granola Launches an Agent-Facing Version: 1M+ Notes Read by Agents Daily — soleio · 2026-11-18