How do you handle attacks and secure your LLM applications?

For those using LLM agents with RAG or web-fetching, how are you currently handling prompt injection? Full blocking, manual review, or hoping it doesn't happen? Wondering what the actual patterns are out there.

And do check out our product too because we are building around that space and would really like to know your point of view about our product and also do leave comment there and if you like you can support too!

launch link:Unplug AI: Security layer to protect LLM applications from attacks | Product Hunt

It is opensource , you can check out our github here: UnplugAI/Unplug: Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.