Agents
Lethal Trifecta
The lethal trifecta is Simon Willison's name for a dangerous mix of three agent capabilities: access to private data, exposure to untrusted content, and the ability to communicate externally.
In depth
The lethal trifecta is Simon Willison's name for a dangerous mix of three agent capabilities: access to private data, exposure to untrusted content, and the ability to communicate externally. When an agent has all three, an attacker can plant instructions in content the agent reads and get it to send the private data out. Willison argues that guardrails which catch most attacks are not enough. The reliable fix is to remove at least one of the three, for example by cutting outbound network access for any agent that reads untrusted input.
Primary source: simonwillison.net
Example
The reliable fix is to remove at least one of the three, for example by cutting outbound network access for any agent that reads untrusted input.
Go deeper at Developers Digest
Hands-on guides, comparisons, and tutorials that cover Agents.
FAQ
Common questions
What is Lethal Trifecta?
The lethal trifecta is Simon Willison's name for a dangerous mix of three agent capabilities: access to private data, exposure to untrusted content, and the ability to communicate externally.
Why does Lethal Trifecta matter for AI developers?
Lethal Trifecta sits in the Agents part of the AI stack. Understanding it helps you make better decisions when building, debugging, and shipping AI features.
Where can I learn more about Lethal Trifecta?
Developers Digest publishes tutorials and videos that cover Agents topics including Lethal Trifecta. Check the blog and YouTube channel for hands-on walkthroughs.
Related
Related terms
Agents
Least Privilege (Agents)
Least privilege is the security rule that every program and user should run with the smallest set of privileges needed for the job, here applied to the tools, credentials, and permissions an agent holds.
Agents
Data Exfiltration (Agents)
Data exfiltration is when an agent is manipulated into sending private data it can reach to a place the attacker controls.
Agents
LLM Tracing
Recording each step of an LLM application as a tree of timed spans, so you can see which prompts, model responses, tool calls, and handoffs happened in one request and how long each took.
Put this concept to work
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever