Securing AI agents against misuse, compromise, and privilege escalation.
Agents
+5
Aug 18, 2026
•
6 min read
A real offensive agent scanned targets, fetched exploits, and then served its operator's secrets to the network. The incident shows why agent security begins with containment.
Jul 29, 2026
The July 28 release makes agent infrastructure easier to scale while moving critical state and security decisions into application code.
Web Security
+7
Browser agents need a security boundary between what they read and what they are allowed to do
+9
Jul 25, 2026
5 min read
AI agents should receive short-lived, task-specific access instead of inheriting the full authority of the person who launched them.
