Latest / Frontier AI Architect

The Confused Deputy: Why Filters Lose to Prompt Injection
A single email made Microsoft 365 Copilot leak data, past three layers of filtering. This episode argues that agent security is about what authority the model's output carries, not about catching bad prompts.
In this episode:
- How EchoLeak worked, and why every defense it passed was a filter
- What happened when researchers attacked 12 published defenses adaptively
- The confused deputy problem from 1988 and why it describes today's agents
- Five controls that hold when the model is fooled, and what each one costs
- The one diligence question investors can ask about any agent
Read the full…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.