• cedws 11 hours ago

    Claude Code’s sandboxing is a complete joke. There should be no ‘off switch.’ Sandboxing should not be opt in. It should not have full read access over the file system by default.

    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.

  • leodido 14 hours ago

    Author here. I helped creating Falco (CNCF runtime security) and built this (Veto) to fix the path-based identity problem we all shipped a decade ago. The dynamic linker bypass in the "where it breaks" section is the part I'm most interested in discussing. It's a class of evasion that no current eval framework measures. Happy to answer questions about the BPF LSM implementation.

    • botanicalfriend 2 hours ago

      On the dynamic linker bypass specifically, have you looked at fapolicyd [1]? It uses fanotify(7) and the top of the README is:

      > The restrictive policy was designed with these goals in mind:

      > 1. No bypass of security by executing programs via ld.so.

      > 2. Anything requesting execution must be trusted.

      One correction on the table: SELinux and AppArmor shouldn't be grouped under "rename-resistant: No". AppArmor is path-based. SELinux labels are on the inode, a rename doesn't change the security context. The copy attack doesn't apply either: a process in sandbox_t creating a file in /tmp gets tmp_t via type transition, and the policy does not grant sandbox_t execute permission on tmp_t.

      [1] https://github.com/linux-application-whitelisting/fapolicyd

      • kilobaud 10 hours ago

        Thanks for your work! Just curious, would it be possible to pad the denylisted binary with arbitrary bytes and circumvent the content hash?

        • walterbell 9 hours ago

          Security policy usually defaults unknown artifacts to low privileges.

      • rogerrogerr 10 hours ago

        > No jailbreak, no special prompting. The agent just wanted to finish the task.

        Good lord, why do people use LLMs to write on this topic? It destroys credibility.

        • tomvault 14 hours ago

          The adversary can reason now, and our security tools weren't built for that.

          Leo di Donato, who helped create Falco, the cloud native runtime security, wrote a technical deep dive into how Claude Code bypassed it's own denylist and sandbox. And introduces Veto, a kernel-level enforcement engine built into the Ona platform.

          • hilti 11 hours ago

            Thank you for this write up. I am still lightyears behind this deep knowledge, but feel like I learned from your post the vocabulary to get started.