AI Security GuruAI Security Guru

Thursday, November 5, 2026 brief

OpenAI AI Pipeline Generates 948 Linux Root Escalation Exploits in 30-Hour Run

The Hacker News

This story is part of the morning brief Anthropic won't fix a Claude Dispatch hole that lets a browser extension run code on your desktop. The reporting lives at the original source.

Read at The Hacker News

A researcher showed that any extension with access to claude.ai can drive Claude Desktop, even on a different machine. Meanwhile a trojaned ARTEX image is serving root shells, Flowise servers are being milked for cloud keys, and OpenAI says GPT-6 Astra quietly goes soft on safety work.

OpenAI AI Pipeline Generates 948 Linux Root Escalation Exploits in 30-Hour Run: AI Security Guru