How are you securing LLM code agents?

What do you mean by securing? Does this mean strictly control AI Agent to behave safely? Or make your data not to get exposed by chatting or so?

Best thing you can do is sandbox them, always check what they want to change with config file (package.json).

Restrict any db operations, for example restrict to run migrations with prisma orm.

Also restrict access to .env or your project configuration with credentials even for dev environment.