---
id: "willison-lethal-trifecta"
title: "The lethal trifecta for AI agents"
creator: "Simon Willison"
url: "https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/"
level: "advanced"
category: "agents"
models: ["any"]
source_date: "2025-06-16"
date_added: "2026-10-18"
---

[Agents and harnesses](/agents/index.md)

# The lethal trifecta for AI agents

by Simon Willison

[Read the original →](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/)

A defensive framework for recognizing risky combinations of agent capabilities and untrusted inputs.

This security discussion identifies a risky combination of sensitive access, untrusted inputs and communication capabilities. We link the analysis for defensive design; no attack instructions or payloads are reproduced here.

Level: [Advanced](/levels/index.md#advanced)
Models: any
Category: [Agents and harnesses](/agents/index.md)
Tags: [security](/tags/security/index.md), [prompt-injection](/tags/prompt-injection/index.md)
Source date: 2025-06-16
Added: 2026-10-18
Last verified: 2026-10-18
Status: ok

Summary in our own words. All rights with the original creator. Correction or removal: DM on X.