# GitHub and Microsoft: 9,791 AI Findings Became 99 Verified OSS Reports

> Source: <https://explainx.ai/blog/github-microsoft-mdash-9791-ai-findings-99-reports-november-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog>
> Published: 2026-11-18 00:00:00+00:00

**Recommendation:** Gate AI-generated security findings behind an automated triage agent for deduplication and validity checks plus human verification before filing private reports; the pilot reduced 9,791 raw flags to 99 reports.
More in the playbook "Designing agent systems": <https://wpnews.pro/playbooks/agent-architecture>

**On November 17, 2026**, **GitHub** and **Microsoft** published the results of a **Codename MDASH** pilot that asks a different question than most AI security marketing: not how many bugs a model can **find**, but how many **verified fixes** reach **maintainers** who are already drowning in **AI-generated noise**. The [official GitHub blog post](https://github.blog/open-source/maintainers/maintainers-dont-need-more-ai-bug-reports-they-need-fixes/?ref=explainx) says **thousands** of possible issues were flagged; after **AI triage** and **hand review**, **six projects** received **99 private reports** with **proof-of-concept** and **suggested patches**. As of **November 15**, maintainers had **fixed 55**, and **14** fixes were already **shipped in a release**. Same-day trade coverage—including [SecurityBrief's recap](https://securitybrief.news/story/github-microsoft-pilot-ai-bug-scans-in-open-source?ref=explainx)—reported **9,791** raw flags citing the pilot figures.

If you run **agents on dependencies** or ship **MCP servers**, this pilot is the counter-pattern to dumping **Scanner-of-the-week PDFs** into public issues. It is also the production sibling to **[MAI Cyber 2 Flash](https://explainx.ai/blog/microsoft-ignite-mai-code-2-seven-models-november-2026)**, which Microsoft announced at **Ignite 2026** while this story was going live.

## TL;DR: what the numbers mean

| Question | Answer (per GitHub, Nov 17, 2026) | 
|---|---|
| **What scanned the code?** | **Codename MDASH** using**Microsoft MAI Cyber** model | 
| **Raw AI flags** | **Thousands** per GitHub; trade press cited**9,791** | 
| **Reports maintainers saw** | **99** private reports after triage and human verify | 
| **Fixed by Nov 15** | **55** , with**14** already in a release | 
| **Human cost** | **Seven** FORGE Lab researchers,**~two days per project** | 
| **Ratio** | Roughly **one maintainer-facing report per 100** raw flags | 

Agents that act on your behalf need rules. [See how explainx helps secure your agents →](https://explainx.ai/agentbeam?src=blog_note)

## Why maintainers said no to more AI bug reports

The post opens with a blunt premise: **AI made finding vulnerabilities fast and cheap**, but **fixing** still needs **human judgment**, and in **open source** that work lands on **volunteers**. GitHub cites **Christian Grobmeier**, a **Log4j** maintainer, saying defenses must beat offensive AI — a line that echoes our [stop blocking defenders letter](https://explainx.ai/blog/stop-blocking-defenders-open-letter-openai-anthropic-cyber-access-2026) coverage on whether **cyber-capable models** should reach **defenders** at all.

Many maintainers already receive **duplicates**, **non-vulnerabilities**, and **low-context** mail. Another raw scan **increases triage load** without shrinking patch queues. That is why **[Google paused OSS VRP intake](https://explainx.ai/blog/google-oss-vrp-bug-bounty-freeze-ai-slop-reports-october-2026)** when **AI-slop reports** spiked, and why **[Warner-style patch rush incidents](https://explainx.ai/blog/ai-vulnerability-patch-rush-outages-warner-congress-november-2026)** happen when executives treat every model output as **CVE-critical**.

The pilot goal was narrower: **send only findings that matter**, and **never send an unverified finding**.

## The five-step pipeline

GitHub documents a fixed sequence. Each step has a named owner.

1. **Find.****Codename MDASH** scans with**MAI Cyber** and**suggests fixes** for what it finds.
2. **Filter.** A**GitHub Security Lab** triage agent, built on**tailored Copilot skills** , removes**duplicates** , checks**validity** , and focuses on**high-impact** bugs so maintainers never see**raw scan output** .
3. **Verify.****Microsoft FORGE Lab** researchers**check every remaining finding by hand** .
4. **Report privately.** Reports go through**[GitHub private vulnerability reporting](https://docs.github.com/en/code-security/security-advisories/guidance-on-reporting-and-writing-information-about-vulnerabilities/privately-reporting-a-security-vulnerability?ref=explainx)** with**proof of concept** and a**suggested fix** .
5. **Fix.** Maintainers choose**what** ,**how** , and**when** to merge; work stays on**GitHub** where**CI** ,**forks** , and**advisories** already live.

This is intentionally **not** a public issue flood. It mirrors how serious vendors want **coordinated disclosure**, and it aligns with **[MCP server security](https://explainx.ai/blog/mcp-tool-provider-misbinding-ai-agents-security-2026)** guidance that **agent tools** should fail closed when **untrusted input** reaches **privileged actions**.

Maintainer security workflow after AI scan triage for Codename MDASH

## Which projects opted in

All six projects are **GitHub Secure Open Source Fund** alumni — each historically received **$10,000** via **GitHub Sponsors** plus **security training**. Maintainers **agreed before the scan**, reviewed reports **privately**, and shared **qualitative feedback** with GitHub:

| Project | Role in stack | Reports mentioned in blog | 
|---|---|---|
| **AutoGPT** | Agent platform | Broken new check caught **three days** after ship | 
| **Caddy** | Web server | **22** reports;**all fixed within a week** | 
| **Express** | Node.js web framework | Reports **cut through noise** | 
| **FastMCP** | MCP framework | Insights **beyond prior AI scanners** | 
| **ImageMagick** | Image processing | **22** reports;**two-person** team | 
| **Netty** | Java networking | Quote: fixing, not finding, is the bottleneck | 

**FastMCP** matters for this audience because **MCP hosts** are now default in **[Claude Code](https://explainx.ai/blog/claude-code-commands-complete-reference-guide-2026)** and **[Copilot Studio workshops](https://explainx.ai/workshops/microsoft-copilot)**. A verified **MCP framework** fix is upstream of thousands of **agent demos**.

## What maintainers actually fixed

GitHub highlights **time-to-fix**, not **model bragging**.

**Caddy** cleared **all 22 reports in a week or less**, using suggested patches **as-is or adapted**. **AutoGPT** had shipped a **broken check**; the private report landed **three days later**, pointed at the **right line**, and the team **exceeded** the suggested patch, merging to production in **under a week**. **ImageMagick** got a report that looked like a familiar class of bug but was not; the summary pointed at **exact lines**, and maintainers **shipped in 15 minutes** — versus **30–60 minutes** for a typical advisory, per their quote.

**Express** maintainers said the short list **cut noise**. **Netty** stressed that **finding** is no longer the bottleneck; **fixing** is. That matches **[Andy Hall auditor false-positive work](https://explainx.ai/blog/andy-hall-ai-audit-agents-false-alarms-malt-r-judge-2026)** on reward hacking and **[Sapper v2 pentest agents](https://explainx.ai/blog/sapper-v2-autonomous-pentest-legion-nuwa-framework-2026)** on autonomous testing — discovery tools multiply; **merge capacity** does not.

## Limits GitHub admits upfront

The blog is explicit that **six projects** is a **small sample**. Lessons are **early**, not proof the method scales everywhere.

**Manual verification does not scale yet.** Seven researchers times **two days per project** is incompatible with scanning **every** popular repo weekly. Meanwhile, **low-quality AI reports** still hit maintainers daily — the problem the pilot tried to absorb, not abolish.

GitHub also lists **open source gaps**:

- Fixes should flow through **private vulnerability reporting** .
- Maintainers need **CI on private forks** to test patches before public merge.
- **Cyber-capable models** should verify**proof-of-concept** before and after fixes — the same capability debate as**[GPT-6 Cyber programs](https://explainx.ai/blog/openai-nato-nci-daybreak-cyber-defenses-november-2026)** and**[MAI Cyber 1 Flash preview](https://explainx.ai/blog/microsoft-mai-cyber-1-flash-mdash-cybergym-july-2026)** .

## How to protect yourself if you depend on these libraries

Consumers of **AutoGPT**, **Express**, **Netty**, or **ImageMagick** should treat **November 15** as a **checkpoint**, not the end of the story.

1. **Turn on Dependabot alerts** for repos you ship.
2. **Watch GitHub Security Advisories** for the six names;**14** fixes were already**released** , but more may land as maintainers finish the remaining**44** open reports from the**99** batch.
3. **Do not rerun public scanners** against those upstreams and file duplicate issues — that recreates the noise this pilot avoided.

For **agent builders**, use **[AgentBeam](https://agentbeam.com/?ref=explainx)** as a **runtime guard** when agents call **shell**, **git**, or **package publish** tools — separate from **static** finding.

## What people search about Codename MDASH

Readers landing from **Hacker News** or **GitHub** trending often ask whether **MAI Cyber** is the same product as **Codex Security** or **Defender agents**. GitHub’s post draws a bright line: **MDASH** is a **Microsoft Security scanning harness**, while **GitHub’s triage agent** is a **Copilot-skills** workflow sitting **between** raw model output and **private vulnerability reporting**. You do not install MDASH as an npm package; maintainers still merge on **GitHub** with their usual **CODEOWNERS** rules.

Another common question is whether **99 reports** means **99 CVEs**. The blog avoids CVE numbering in the pilot recap; maintainers received **private advisories** with **proof-of-concept** and **suggested fixes**, then chose severity and disclosure timing. **55 fixes by November 15** counts **merged remediations**, not a public CVE batch count.

Teams comparing **Ignite-week** announcements should read **[MAI Cyber 2 Flash preview status](https://explainx.ai/blog/microsoft-ignite-mai-code-2-seven-models-november-2026)** before assuming the **next** open source sweep already runs on **Cyber 2**.

## What GitHub and Microsoft do next

The post ties forward motion to three threads:

- **Private reporting product** — lessons feed**GitHub Security Lab** investments to reduce**low-quality** inbound mail.
- **MAI Cyber 2** — Ignite-week model refresh; future scans may use the newer stack described in**[Ignite model roundup](https://explainx.ai/blog/microsoft-ignite-2026-complete-coverage-every-announcement-november-2026)** .
- **Secure Open Source Fund expansion** — future alumni may get**checked AI scans** plus**Copilot Max** , extending the**216-project** fund narrative (**4,000+** vulnerabilities fixed in software downloaded**20B+** times monthly, per GitHub).

If you maintain a funded or critical repo, enable **`gh-secure`** and **private vulnerability reporting** now so researchers (human or vendor-run) have a **single intake**, as **[Codex Security open source](https://explainx.ai/blog/openai-codex-security-cli-sdk-open-source-july-2026)** tooling spreads.

## What people building AI security should copy

GitHub ends with a **sender standard** anyone running **agentic scanners** should paste into runbooks:

- **Check** every finding against**project knowledge** ,**threat model** , and**SECURITY.md** .
- **Report privately** .
- **Include a suggested fix** ; let maintainers set pace.

That is the inverse of **leaderboard hacking** on **[ExploitBench-style](https://explainx.ai/blog/revolut-openai-codex-fincrime-gpt-5-5-enterprise-story-2026)** demos. It also complements **[external sandboxes for coding agents](https://explainx.ai/blog/external-sandboxes-coding-agents-prime-radiant-willison-november-2026)** — isolate execution, but still **ship patches** through **maintainer-owned** merge paths.

## How this differs from shipping a security model only

**MAI Cyber 2 Flash** answers “can a model **find** bugs?” **Codename MDASH** answers “can a **pipeline** deliver **mergeable fixes**?” That distinction matters for **CISOs** comparing **Microsoft Perception** playbooks to **AppSec** backlog reality.

GitHub’s numbers imply **~1%** yield from raw flags to maintainer reports. Security vendors often cite **10x** noise reduction; here the **denominator** is public. If your team runs **weekly agent scans**, benchmark **your** signal rate before you promise **leadership** the same **99-report** outcome.

**Dependabot** and **CodeQL** still matter: this pilot **supplements**, not replaces, **deterministic rules**. **[Agent autofix](https://explainx.ai/blog/microsoft-agent-framework-pypi-1-26-credential-stealer-november-2026)** features on **private repos** ride a different rail — **maintainer consent** plus **verified patches**.

## Supply-chain ripple for MCP and agent frameworks

**FastMCP** participation is strategically important. **MCP** is the **default integration spine** for **[Claude Code](https://explainx.ai/blog/claude-code-commands-complete-reference-guide-2026)**, **[Copilot agents](https://explainx.ai/blog/microsoft-copilot-autopilot-m365-frontier-rollout-november-2026)**, and a growing share of **internal tools**. A **verified fix** in **FastMCP** propagates through **thousands of forks** faster than a **blog CVE**.

**AutoGPT**’s broken-check anecdote shows **agent frameworks** ship **guardrails** that themselves become **attack surface**. Teams running **autonomous pentest** demos should read **[Sapper v2](https://explainx.ai/blog/sapper-v2-autonomous-pentest-legion-nuwa-framework-2026)** alongside this pilot — **offense automation** and **defense automation** share **the same maintainers**.

## Related reading

*Figures and quotes follow GitHub and Microsoft November 17, 2026 blog text unless noted as maintainer quotes.*
