Ask HN: Do you know what data your AI coding agent sends to the cloud?

Post by zambelli » Mon, May 18, 2026, 8:19 PM UTC

lbrauer wrote: post #3

zambelli wrote: post #2

I trust the tool in that I don't send anything sensitive in there! Unless I built it, I assume it's going somewhere. We have a policy at work around this where our most sensitive data can only be passed to on prem models. That being said, I have no evidence of anything going to the cloud or frontier providers doing anything with chat history other than storing it for later. Self-hosted + custom harness for anything I…

Makes sense. Does your custom harness give you a record of what actually crossed the boundary, or is it mostly trust-based blocking?

Post by unknown_2045 » Tue, May 19, 2026, 6:57 AM UTC

boundless88 wrote: post #13

I'm really curious, if you use open-source tools like Codex. And you actually go through the source code carefully to make sure there are no backdoors, doesn't that mean you can use it without worrying about your data getting leaked—at least to some degree?

Post by warren455 » Tue, May 19, 2026, 10:06 AM UTC