Re:Design Patterns for Securing LLM Agents Against Prompt In...
by ntonozzi on Friday June 13, 2025 @02:10PM
(#44270769)
This approach is so limiting it seems like it would be better to change the constraints. For example, in the case of a software agent you could run everything in a container, only allow calls you trust to not exfiltrate private and make the end result a PR you can review.
[ Parent
| on HN ]
There are no comments on this comment yet.