RiskWire Real-time vulnerability intelligence

This week Pricing Live dashboard

High 7.5

CVE-2026-33096

Anthropic Internal AI Model Generates Proof-of-Concept Exploits for Chrome, Safari, Windows, and Linux

Vendor / product: Google Chrome, Apple Safari, Microsoft Windows, Linux

Public PoC: Yes

First tracked by RiskWire: 2026-10-28

Sources & citations (2)

Le modèle d'IA non publié d'Anthropic enchaîne des failles pour créer des exploits fonctionnels pour Chrome, Safari, Windows et Linux news.lavx.hu · 2026-10-28
Anthropic's Unreleased AI Model Chains Flaws Into Working Chrome, Safari, Windows and Linux Exploits thehackernews.com · 2026-10-28

References

View on NVD ↗ View on MITRE CVE ↗ Search CISA ↗ KEV lookup tool

See CVE-2026-33096 in context

RiskWire tracks every exploited CVE this week, cross-referenced against CISA KEV with federal remediation deadlines. Filtered to your vendor stack.

Book a 20-min demo →