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 kay_o on Saturday November 07, 2026 @06:03PM (#50408897)

For some reason claude code hates using the read/write/grep tools and defaults to complex sed, awk, grep Bash:* runs which results in always consistently ignoring auto mode due to the classifier not knowing what to do with a 10-line long bash pipe instead of a read + pre/post read and write hooks being ignored and not firing, what is up with that?

[ Parent | on HN ]

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by dcrazy on Saturday November 07, 2026 @06:29PM (#50409043)

I use a hook to deny `grep /` and `find /`.

[ Parent | on HN ]

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by awfulneutral on Saturday November 07, 2026 @06:43PM (#50409124)

I had claude write a hook to deny `find /`. It tested it thoroughly. Much later I learned that the hook denied `find /` but allowed everything else that existing permissions denied, like running whatever random python/bash code it wanted without asking.

[ Parent | on HN ]

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by awfulneutral on Saturday November 07, 2026 @06:48PM (#50409151)

I don't understand this either, it makes commands really hard to parse. It seems like 90% of what claude does could be going through some mcp tool that could be easily sandboxed instead of bash gibberish.

[ Parent | on HN ]

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by kay_o on Saturday November 07, 2026 @07:09PM (#50409288)

If it was human approval ? Read("./file.name") then Bash("docker compose run unit-tests"), sure, I can read that fine !

As I was reading your post I got another approval request that auto-mode did not understand. It was a single Bash call !!23!! lines tall on a retina mac display with six different variables. If anything this is the cause of approval fatigue and auto mode does nothing helpful when this is every call. I also have in my claude.md and global instructions to use tool calls rather than bash grep/cat/find, which are disregarded.

[ Parent | on HN ]

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by awfulneutral on Saturday November 07, 2026 @07:49PM (#50409512)

Yeah I agree, I didn't used to feel approval fatigue but lately the huge bash chains are giving it to me. I haven't even tried auto mode. I'm just sure it has some definition of "safe" that does not align with my own.

[ Parent | on HN ]

Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12... by kay_o on Saturday November 07, 2026 @08:30PM (#50409720)

I'm not sure when claude started preferring huge bash chains but auto mode tends to decline most of them and drop to a permission prompt -- getting rid of the use of auto mode -- because it refuses to handle anything chained with expansions, variables or similar items

[ Parent | on HN ]