# Google's AVDH AI Finds 100+ Critical Security Vulnerabilities in Two Days

> Google has revealed an internal system called AVDH, short for Agentic Vulnerability Discovery Harness, that spent two days combing through source code and surfaced more than 100 verified high-severity security flaws. Across its run it scanned tens of millions of lines of code and generated tens of thousands of findings, which human reviewers then triaged. What makes the disclosure notable is that AVDH had already been running quietly inside Google's Mandiant security arm for about ten months before the company said anything publicly. The result cuts both ways. Tools like this promise defenders a way to find and patch bugs at a pace no human team could match, but the same capability accelerates discovery for everyone, and the number of catalogued vulnerabilities keeps climbing, with 2026 on track for more than 66,000 CVEs. As agentic scanners get better at reading code, the pressure shifts to whether organizations can actually fix what the machines keep dredging up.

_Section: [Daily AI Updates](https://www.wortins.com/daily-ai) · Source: Help Net Security · Published Wednesday, September 2, 2026_

## Wortins' read

Google has revealed an internal system called AVDH, short for Agentic Vulnerability Discovery Harness, that spent two days combing through source code and surfaced more than 100 verified high-severity security flaws. Across its run it scanned tens of millions of lines of code and generated tens of thousands of findings, which human reviewers then triaged. What makes the disclosure notable is that AVDH had already been running quietly inside Google's Mandiant security arm for about ten months before the company said anything publicly. The result cuts both ways. Tools like this promise defenders a way to find and patch bugs at a pace no human team could match, but the same capability accelerates discovery for everyone, and the number of catalogued vulnerabilities keeps climbing, with 2026 on track for more than 66,000 CVEs. As agentic scanners get better at reading code, the pressure shifts to whether organizations can actually fix what the machines keep dredging up.

## Source

[Read the full story at Help Net Security](https://www.helpnetsecurity.com/2026/08/19/google-mandiant-avdh-ai-vulnerability-discovery-tool/)

## Related coverage

- [Illinois AI Safety Measures Act signed](https://www.wortins.com/story/illinois-ai-safety-measures-act-signed-3817d5cc) — [Capitol News Illinois](https://capitolnewsillinois.com/news/pritzker-signs-landmark-ai-regulation-bill-that-aims-to-mitigate-risks)
- [Meta Muse Spark 1.3 release](https://www.wortins.com/story/meta-muse-spark-1-3-release-31c51c09) — [Meta AI Research](https://research.meta.ai/blog/introducing-muse-spark-1-3)
- [Backbone Raises €4M for AI-Powered Food Quality and Compliance](https://www.wortins.com/story/backbone-raises-4m-for-ai-powered-food-quality-and-complianc-dd7261f9) — [Tech.eu](https://tech.eu/2026/09/03/backbone-raises-eur4m-for-automated-food-quality-and-compliance/)
- [xorlab Raises €5M Series A to Expand Sovereign Email Security Across Europe](https://www.wortins.com/story/xorlab-raises-5m-series-a-to-expand-sovereign-email-security-5a8c523b) — [EU-Startups](https://www.eu-startups.com/2026/09/zurich-based-xorlab-secures-e5-million-to-scale-sovereign-email-security-across-europe/)
- [Catch AI $5M seed for executive assistant](https://www.wortins.com/story/catch-ai-5m-seed-for-executive-assistant-991243fa) — [Tech Startups](https://techstartups.com/2026/09/03/catch-emerges-from-stealth-with-5m-to-build-an-ai-executive-assistant-that-handles-admin-work-for-you/)
- [Google voice features in Gmail, Docs, Keep](https://www.wortins.com/story/google-voice-features-in-gmail-docs-keep-458d6a6a) — [TechCrunch](https://techcrunch.com/2026/09/03/google-launches-ai-voice-features-in-gmail-docs-and-keep/)

---

_Curated and written by [Wortins](https://www.wortins.com) — The daily AI briefing. Every story links to its original source; the "Wortins read" on each is our own original analysis. [About Wortins & our editorial approach](https://www.wortins.com/about)._