Re:Delimiters won’t save you from prompt injection
by graypegg on Thursday May 11, 2023 @06:56PM
(#35909454)
Yes totally. This really is no different than any other code injection vulnerability. Only allow symbols that you expect, and don't concatenate user input and logic unless the bounds between the two are guaranteed to be explicit.
[ Parent
| on HN ]
Re:Delimiters won’t save you from prompt injection
by rain1 on Saturday May 13, 2023 @01:52AM
(#35925971)
this is not correct
Re:Delimiters won’t save you from prompt injection
by qingdao99 on Saturday May 13, 2023 @03:37AM
(#35926425)
> don't concatenate user input and logic unless the bounds between the two are guaranteed to be explicit
Which is achieved how for an LLM?
Re:Delimiters won’t save you from prompt injection
by PeterisP on Saturday May 13, 2023 @09:36AM
(#35928230)
> don't concatenate user input and logic unless the bounds between the two are guaranteed to be explicit.
Well that's kind of the whole problem - LLM-based agents inherently work by literally concatenating logic with user input, and the bounds aren't guaranteed to be explicit. There is a discussion about finding a way to implement such bounds, but we don't have a good solution yet.