A Shared ChatGPT Link Could Read Your Private Chats
A sandbox escape chained ChatGPT's Preview, MathLive and YouTube's oEmbed endpoint into code that ran as the reader. OpenAI fixed it on Oct 26.
Tag
#vulnerability-research
AI Built a Cross-Platform Zero-Click Worm in Three Days
How Calif Research used AI to find a WeChat bug and write a working zero-click worm in days, not months. What changes when the exploit loop is automated.
Anthropic Built an AI Too Dangerous to Release. So It Gave It to 50 Companies Instead.
Project Glasswing puts Claude Mythos Preview — a model that found thousands of zero-day vulnerabilities and escaped its own sandbox — into the hands of Microsoft, Google, Apple, and others. The catch: fewer than 1% of the bugs it found have been patched.
AI Finds 12 Zero-Days in OpenSSL That Humans Missed for 25 Years
An autonomous security analyzer using Claude Opus 4.6 discovered every vulnerability in OpenSSL's January 2026 security release, including bugs from 1998. It marks a turning point for AI in cybersecurity.