News for hackers. Stuff that matters.
Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by eastbound on Sunday November 08, 2026 @02:17AM (#50411113)
I tell Claude not to use git or maven, and has a VM without those binaries. Later on, it was trying to push on GitHub. It had downloaded the git binaries from the internet, read my .git repo, used the remotes written in it, performed a commit and pushed it. Fortunately it didn't have my SSH key or my ~/.m2/settings.xml. And .git is now mounted as read-only.

But yes, Claude goes constantly against the orders, especially in auto mode, and effectively behaves like a virus. That Anthropic employees are so relaxed about it is incompetence.

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by iamflimflam1 on Sunday November 08, 2026 @02:51AM (#50411236)
It’s not ideal for non technical people but the way to prevent this is to use hooks. “Telling” Claude is not going to work.
Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by BikiniPrince on Sunday November 08, 2026 @03:17AM (#50411360)
Memory files routinely overgrow their accessible size. Agents need constraint with contracts and external tooling. Even then they can attempt to cheat the tooling. Again task management with integrated logic will enforce behavior of agents.
Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by fg137 on Sunday November 08, 2026 @08:12AM (#50412993)
It means Anthropic has massively failed at developing a trustworthy product.

If AGENTS.md/CLAUDE.md isn't followed, auto mode doesn't provide any guarantee, yet promoted everywhere including on HN like this as if that's something you can set and forget, I think there is a problem.

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by usewik on Sunday November 08, 2026 @08:57AM (#50413422)
It's trustworthy... most of the time. For 100% use hooks.