If you're building agents, this is worth knowing. Simon Willison (who coined the term "prompt injection") describes three capabilities that are individually fine but devastating together, the lethal trifecta includes:
-
Access to private data (such as internal databases, emails, etc.)
-
Exposure to untrusted content (like web pages and external text)
-
The ability to exfiltrate data (a tool or a channel of sorts that reaches the outside world)
Combine all three in one agent and you've got a perfect storm: untrusted content can hijack the agent into reading private data and then persuade the agent to send it out.
To teach the lethal trifecta, I built a Gandalf-style puzzle: 10 levels, each a real injection concept, with the full trifecta as the final level. It's free, there's no sign up and initially it's beginner-friendly.
See if you can chain all three together and complete the trifecta!
Comments URL: [https://news.ycombinator.com/item?id=48950221](https://news.ycombinator.com/item?id=48950221)
Points: 3