Skip to main content
Mallory
← Back to News
zero-day-acquisitionendpoint-software-vulnerabilityopen-source-dependency-vulnerability

AI Model Reportedly Finds V8 Zero-Day in 13 Minutes for $4.24

Vulnerability Disclosure · 2 sources · Updated 14h ago · First seen Nov 16, 2026

AI Model Reportedly Finds V8 Zero-Day in 13 Minutes for $4.24

Xint.io reportedly found that an AI model could identify a Google V8 vulnerability in 13 minutes at a usage cost of $4.24, highlighting falling barriers to AI-assisted vulnerability discovery. In a restricted source-code test involving seven models, only GPT 6 Sol, GPT 5.6 Sol, and Claude Opus 5 identified the privately reported type-confusion flaw, identified in the reports as CVE-2026-102321, which could enable remote code execution. A February 2026 attempt had failed after 25 hours and $350, while GPT 6 Sol succeeded in September using a guided prompt.

The results suggest that improving models and declining inference costs could make vulnerability discovery more accessible to attackers and defenders, but they do not demonstrate autonomous discovery across arbitrary software: the tests used restricted source code, expert guidance remained important, and some attempts required additional prompting. The reports establish neither active exploitation nor patch availability. Security teams should evaluate AI-assisted testing within authorized workflows while maintaining layered defenses, including hardening, zero-trust access controls, network segmentation, and endpoint monitoring.

Do you run this?See affected versions and whether adversaries are exploiting it.
Check your exposure
Event timeline

How this story unfolded

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

5 events · Feb 2026 – Sep 2026
  1. Reported Nov 16, 202617h ago

    Claude Opus 5 identifies V8 flaw on its first attempt for $43.40

    Claude Opus 5 identified the target vulnerability on its first attempt at a reported cost of $43.40. It was one of only three successful models among the seven Xint evaluated; the sources do not date this test.

    AI finds zero-day flaws for just $4 now - even mediocre hackers can cash in - ZDNET
  2. Reported Nov 16, 202617h ago

    Xint researcher privately reports Google V8 type-confusion vulnerability

    Xint researcher Taisic Yun privately reported a Google V8 vulnerability through Google's Vulnerability Reward Program. The articles identify it as CVE-2026-102321, a type-confusion flaw capable of enabling remote code execution.

    AI finds zero-day flaws for just $4 now - even mediocre hackers can cash in - ZDNET
  3. Sep 2026

    GPT 6 Sol identifies V8 flaw in 13 minutes for $4.24

    GPT 6 Sol identified the same vulnerability in 13 minutes at a reported cost of $4.24 using its first guided prompt. The result came from a controlled vulnerability-discovery test, not observed exploitation.

    AI finds zero-day flaws for just $4 now - even mediocre hackers can cash in - ZDNET
  4. Jul 2026

    GPT 5.6 Sol identifies V8 flaw in 44 minutes for $22

    GPT 5.6 Sol identified the target vulnerability in Xint's restricted-source test in 44 minutes at a reported cost of $22. The model required two prompts to find the flaw.

    AI finds zero-day flaws for just $4 now - even mediocre hackers can cash in - ZDNET
  5. Feb 2026

    AI models fail to find V8 flaw after 25 hours and $350 in testing

    In Xint's February testing, the best models tested failed to identify the privately reported V8 vulnerability after 25 hours and $350 in scanning costs. Researchers restricted the search to selected source files that included the vulnerable file.

    AI finds zero-day flaws for just $4 now - even mediocre hackers can cash in - ZDNET
Linked entities

Related entities

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

Open in app →

Affected products

1 linked
V8

Organizations

5 linked
DeepseekAnthropicOpenaiGoogleZ.ai
Do you run this?See whether adversaries are exploiting this yet, and where the affected versions run in your environment.
Check Your Exposure
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.