Post #4036221
2026-07-16 05:04 UTC
Yes and no. There are no guardrails on its output, so it will happily emit sudo rm -rf /*. But the “harness” of the agents gets to check if this gets executed. The default is usually “ask every time”, but you can change that to “everything is allowed” or “every invocation of ls and grep is allowed”. Problem is, when users get tired to constantly proof read and check every single command (and it will constantly emit commands) and then just hit “allow everything for this session” or such. Or when a user defines ls .* \| grep .* is a regex that defines that this is always OK to run but don’t see that it also matches any command after the grep that could do whatever with that data.
Basically: the only safe way is to manually check every single command and you will be annoyed quickly and let you guard down.
Replies (2)
-
@Mr_WorldlyWiseman@lemmy.blahaj.zone 2026-07-16 06:28
But the harness doesn’t actually prevent Claude Code from running commands. It just tells the model to end with a question instead of running the command directly. I haven’t actually read the source code though, just an anecdote from it running commands even when “ask every time” is enabled.
-
@flying_sheep@lemmy.ml 2026-07-16 07:03
Claude’s harness parses pipes and asks for permission for each individual command. Of course you’re right about the issues, e.g. when it creates a script file to execute and you allow that for the session, it can edit it and then re-execute it without your further input.