Agent Security
Securing AI agents against misuse, compromise, and privilege escalation.
Agents
+5
Aug 18, 2026
•
6 min read
How an AI Agent Exposed Its Hacker's Operation
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.
Agents
+5
Jul 29, 2026
•
6 min read
MCP Goes Stateless in Its Biggest Specification Update Yet
The July 28 release makes agent infrastructure easier to scale while moving critical state and security decisions into application code.
