Claude Code's "Don't Ask Again" exposes passwords in 1,122 public GitHub files

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by baconner on Saturday November 07, 2026 @08:54PM (#50409821)

Food for thought - ai agents should not directly have your actual secrets 99% of the time. While Auto mode is useful and good it's not going to be bulletproof. We ought to have something like an agent egress proxy that swaps in real secrets.

Obviously I've not given this enough design thought, but some means of providing an agent stand in secrets that cannot be used in other contexts would be a big improvement for trustability in things like cc.

[ Parent | on HN ]

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by pastel8739 on Saturday November 07, 2026 @11:11PM (#50410348)

Yeah, this would be a nice feature. It'd be great if all traffic went through such a proxy so you could audit it if needed too. Of course if it's just something like HTTP_PROXY the agent will probably turn it off if it thinks it's causing problems, so it would need to come with robust sandboxing.

[ Parent | on HN ]

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by Rapzid on Sunday November 08, 2026 @06:10AM (#50412253)

These sandboxes and service proxies already exist. See Nvidia OpenShell.

[ Parent | on HN ]