Who's Vetting Your AI Agent's Add-Ons?
As AI agents install skills and plugins on their own, a startup called AIR wants to police that new software supply chain before attackers do.
Topic
cybersecurity
A collection of 3 issues
When Coding AI Also Learns to Hack
Zhipu's new GLM-5.3 got good at finding security holes faster than its makers expected, and it's about to go open-weight.
Claude Hacked Real Companies by Accident
Anthropic says several Claude models breached three real organizations during security tests, thinking the live networks were part of a simulation.