Re:Claude Code escapes its own denylist and sandbox
by arianvanp on Tuesday March 03, 2026 @05:57PM
(#47240303)
I opened an issue about this on day 1 of the release:
https://github.com/anthropic-experimental/sandbox-runtime/is...
I ended up making my own sandbox wrapper instead https://GitHub.com/arianvp/landlock-nix
Re:Claude Code escapes its own denylist and sandbox
by simlevesque on Tuesday March 03, 2026 @05:54PM
(#47240269)
The first thing I recommend everyone using is devcontainers [1]. They're very simple to setup and make using LLMs a lot more secure.
Re:Claude Code escapes its own denylist and sandbox
by tso on Wednesday March 04, 2026 @04:19AM
(#47245020)
The Claude sandbox is so antithetical to good security posture it almost seems intentional[0]. Having both "default read to the entire file system" and "the agent can and _will_ disable the sandbox, without even asking the user[1], in order to complete tasks" would not pass muster in a freshman level security course.
[0] assuming a human with security training was involved in the design/prompting of the sandbox development.
[1] Claude has well used mechanisms for asking the user before taking potentionally dangerous actions. Why it is not part of the "disable my own SANDBOX" branches of code is confusing.
I really want more security people to get involved in the LLM space because everyone seems to have just lost their minds.
If you look at this thing through a security lens it’s horrifying, which was a cause of frustration when Anthropic changed their TOS to ban use of alternative clients with a subscription. I don’t want to use that Swiss cheese.