LESSWRONG
LW

Language Models (LLMs)Privacy / Confidentiality / SecrecyAI
Frontpage

13

[Linkpost] The lethal trifecta for AI agents: private data, untrusted content, and external communication

by Gunnar_Zarncke
17th Jun 2025
1 min read
3

13

This is a linkpost for https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/
Language Models (LLMs)Privacy / Confidentiality / SecrecyAI
Frontpage

13

[Linkpost] The lethal trifecta for AI agents: private data, untrusted content, and external communication
2Seth Herd
8Gunnar_Zarncke
2Seth Herd
New Comment
3 comments, sorted by
top scoring
Click to highlight new comments since: Today at 10:41 AM
[-]Seth Herd24d20

Seems interesting. But this isn't lethal at all, and it's a little disturbing to hear the term used this way, as though this person has never even thought about AGI risks. Hopefully security problems and prompt injections are one route to increasing public awareness of the complexity and unreliability of AI behavior.

Reply
[-]Gunnar_Zarncke23d80

hm, yes, "lethal" is maybe too hard, esp. in the title, but I didn't choose that. Also, it is not unusual in colloquial use:

ChatGPT: What does a security researcher mean when a user action is lethal?

When a security researcher describes a user action as lethal, they typically mean it triggers a condition that irreversibly compromises the system's integrity, confidentiality, or availability—often without recourse for mitigation after the fact. This could include actions like clicking a malicious link that installs a rootkit, reusing credentials on a phishing site leading to credential stuffing, or executing a command that bricks a device. "Lethal" underscores not just the severity but also the finality: the action doesn't just degrade security but catastrophically collapses it, often silently and instantly.

Reply
[-]Seth Herd23d20

Ah I see. I didn't know that use of the word.

Reply
Moderation Log
Curated and popular this week
3Comments

TL;DR from the post by Simon Willison:

The lethal trifecta of capabilities is:

  • Access to your private data—one of the most common purposes of tools in the first place!
  • Exposure to untrusted content—any mechanism by which text (or images) controlled by a malicious attacker could become available to your LLM
  • The ability to externally communicate in a way that could be used to steal your data (I often call this “exfiltration” but I’m not confident that term is widely understood.)

This combination can let an attacker steal your data.

  • The lethal trifecta (diagram). Three circles: Access to Private Data, Ability to Externally Communicate, Exposure to Untrusted Content.