Skip to main content
Mallory
← Back to News
ai-platform-securityopen-source-dependency-vulnerabilitystandards-framework-update

Google Mandiant Unveils AI Vulnerability Discovery System After Finding 100+ Flaws

Emerging Technology Risk · 2 sources · Updated 3mo ago · First seen Aug 19, 2026

Google Mandiant Unveils AI Vulnerability Discovery System After Finding 100+ Flaws

Google-owned Mandiant disclosed an internal AI-assisted vulnerability discovery platform, the Agentic Vulnerability Discovery Harness (AVDH), saying it identified more than 100 verified high-severity software flaws in two days during a live investigation tied to stolen corporate repositories. Mandiant said the system has been used internally for about ten months, scanned tens of millions of lines of code, and produced tens of thousands of findings, including dozens of assignable vulnerabilities affecting widely used web extensions and open-source projects.

Mandiant said the work has already led to 12 assigned CVEs, including CVE-2026-13242 and CVE-2026-55803, with roughly another dozen cases still in coordinated disclosure. The company described AVDH as a pipeline of specialized AI agents handling threat modeling, entry-point discovery, context enrichment, hypothesis generation, and validation, while stressing that human analysts still review threat models and manually reproduce exploits before findings are accepted. To reduce false positives, agents are designed to challenge one another’s conclusions and apply consultant-authored rules by language, framework, and vulnerability type; Mandiant also said it evaluated the system on synthetic intentionally vulnerable codebases rather than public benchmarks to avoid model-training contamination.

New surface, new adversariesTrack how attackers are adapting to this technology.
Track this risk
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

4 events · 2026 – Aug 18, 2026
  1. Reported Aug 19, 20263mo ago

    AVDH finds 100+ high-severity flaws in two-day live investigation

    During a live investigation involving stolen corporate repositories, Mandiant said AVDH identified more than 100 verified high-severity vulnerabilities in just two days. The company presented this as a real-world demonstration of the system's effectiveness.

    Google’s AI security agents found 100+ critical software vulnerabilities in just two days - Help Net Security
  2. Reported Aug 19, 20263mo ago

    Mandiant begins operating AVDH internally

    Mandiant said its Agentic Vulnerability Discovery Harness (AVDH), an AI-assisted source-code vulnerability discovery system, has been running internally for ten months. During that period it scanned tens of millions of lines of code and generated tens of thousands of findings.

    Google’s AI security agents found 100+ critical software vulnerabilities in just two days - Help Net Security
  3. Aug 18, 20263mo ago

    Google publishes Mandiant blog disclosing AVDH

    Google published a Threat Intelligence blog post describing Mandiant's internal AVDH system, its multi-agent workflow, and its use in agentic source-code review. The disclosure emphasized human validation and techniques intended to reduce false positives.

    Staying Ahead of Adversarial AI Through Agentic Source Code Review | Google Cloud Blog
  4. 2026

    AVDH work leads to 12 assigned CVEs and more disclosures underway

    Mandiant said findings from AVDH have already resulted in 12 assigned CVEs, including CVE-2026-13242 and CVE-2026-55803. It also said about a dozen additional vulnerabilities are under active disclosure.

    Google’s AI security agents found 100+ critical software vulnerabilities in just two days - Help Net Security
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.

Open in app →

Organizations

1 linked
Mandiant
Do you run this?Follow how adversaries are adapting to this technology, and where it touches your stack today.
Track This Risk
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.