Skip to content
AI Security

lethal trifecta

AI security interview questions tagged lethal trifecta, across every topic.

2 questions · 1 unlocked for you
Open full answer →
Open full answer →

Concepts behind "lethal trifecta"

Explanations of the mechanisms these questions rely on.

Foundational
Agent & MCP Security
The Lethal TrifectaThe lethal trifecta, a term coined by Simon Willison in 2025, is the combination of three capabilities in one AI agent: access to private data, exposure to untrusted content, and the ability to communicate externally. With all three, an instruction hidden in untrusted content can make the agent read private data and send it out. Use the combination to trace a possible disclosure path, then remove unnecessary capabilities or enforce restrictions outside the model. A narrower token alone does not revoke an older, broader token.
Explore the full curriculum →