1/🔒Worried about giving your agent advanced capabilities due to prompt injection risks and rogue actions? Worry no more! Here's CaMeL: a robust defense against prompt injection attacks in LLM agents that provides formal security guarantees without modifying the underlying model!

I'm in Munich to attend SaTML, where we're presenting CaMeL at the poster session later today and during the Safety and Alignment session tomorrow after lunch. Feel free to reach out if you're around and wanna chat about agents security!

I have no clue how this works but it would be so funny if instead of bribing one could just prompt inject