As a precaution I would probably never pass secrets directly to the agent at all. Something like a placeholder format where the actual substitution happens at execution time so the LLM never sees the real value. Keeps things cleaner if something ever goes wrong.
devendra1162 days ago | | | parent | | on: 47737207
is there any tool that can do this ?
para_parolu2 days ago | | | parent | | on: 47737298
I use mitmproxy outside of agent vm
devendra1162 days ago | | | parent | | on: 47737364
interesting, how do you use mitmproxy for calling openAI llm ? or what exactly you use it for ?