-
The Sandbox Is Not the Boundary You Think It Is
Independent research is revealing that agent sandboxes have boundaries permission models did not anticipate.
-
An AI Agent Just Talked Its Way Into Your Software Supply Chain
Reputation farming by autonomous agents and the underlying identity gap that lets it work.
-
From Prediction to Pattern: Google's AI Threat Tracker Validates the Case for Agent Trust
Google's threat tracking confirms the GTG-1002 incident pattern, and underlines the case for explicit agent identity.
-
The Authenticated Session Problem
Why auto-browse changes the threat model for everyone, not just the AI vendors.
-
Board Governance in the Agentic Era: What Risk Committees Need to Know
What boards and risk committees need to understand about agentic AI before it lands in their next operational risk pack.
Book