News for hackers. Stuff that matters.
Re:Design Patterns for Securing LLM Agents Against Prompt In... by Onawa on Friday June 13, 2025 @01:09PM (#44270288)
Very helpful Simon! I have definitely been hesitant to spin up any agents even in sandboxes that have access to potentially destructive tools, but this guiding principle does ease my concerns a bit.

There are no comments on this comment yet.