Re:Design Patterns for Securing LLM Agents Against Prompt In...
by simonw on Friday June 13, 2025 @11:15AM
(#44269293)
Yeah, this paper is refreshingly conservative and practical: it takes the position that robust protection against prompt injection requires very painful trade-offs:
These patterns impose intentional
constraints on agents, explicitly
limiting their ability to perform
arbitrary tasks.
That's a bucket of cold water in a lot of things people are trying to build. I imagine a lot of people will ignore this advice!
Re:Design Patterns for Securing LLM Agents Against Prompt In...
by NoMoreNicksLeft on Friday June 13, 2025 @11:24AM
(#44269376)
LLMs are too useful to allow the commoner access to them. The question remains, how best to fleece those commoners with perceived utility while providing them none?
Re:Design Patterns for Securing LLM Agents Against Prompt In...
by theHolyTrynity on Thursday June 19, 2025 @06:18AM
(#44317168)
yes agree most hype around agents is around stuff that ignore these patterns
i think basically all of them involve reducing the "agency" of the agents though - which is a fine tradeoff - but i think one should be aware that the Big Model folks dont try to engineer any of these and just collect data to keep reducing injection risk. the tradeoff of capability maxxing vs efficiency/security often tends to be won by the capabilitymaxxers in terms of product adoption/marketing.
eg the SWE Agent case study recommends Dual LLM with strict data formatting - would like to see this benchmarked in terms of how much of a perfomance an agent like this would be, perhaps doable by forking openai codex and implementing the dual llm.