Monday 16 November
Global

Your region, kept on this device.

Token says its own AI agent broke three core security principles by default

Severity
Info
Sources
1

A security company built an AI agent that ignored the basic safety rules it normally recommends to customers. The article says the agent was built to act inside a user's logged-in browser session, and the write-up explains how such agents should be defended.

Like I’m new · Written by AI from 1 source · Wrong?

What to do

  1. No action needed.

Written by AI from the sources, checked against them

Full story timeline · 1 update

  1. Wed 11 NovemberWe Built An Agent That Broke All of Our Security Rules. Here's What We Learned.The Hacker News

Who reported · 1 outlet

The Hacker News

Report a problem