The Claude Code changelog lists version 2.1.325 as its newest release. It is mostly a security and permissions release, and one default has changed.
The change that can surprise teams
Sandboxed Bash commands now follow the normal permission flow by default. Previously they ran without prompts. Teams that want the old behaviour must set sandbox.autoAllowBashIfSandboxed: true, and organisations that turn the sandbox on through managed settings must set it in their highest-ranking managed source. After updating, developers may see permission prompts that were not there before.
Security fixes
- A security issue in how zstd-compressed responses are decoded is fixed.
- Some compound Bash commands could previously run without asking. They now ask.
- Deny and ask rules were not always applied after a restart, or after changing directory. Those gaps are closed.
- The sandbox now refuses writes to
.claudesettings, skills, agents, commands and hooks in added directories, and protects a worktree’s settings, hooks and shared git folder more fully. - The programs the sandbox starts for its own use now run without Claude Code’s sign-in tokens and API keys in their environment.
Why it matters
An AI coding tool can read files and run commands on a developer’s machine. Permission rules and sandboxes are what limit the damage when something goes wrong. A release that closes gaps in those rules is good news, but it also shows that the rules are living configuration, not a one-off setup.
So what
Ask your development partner three questions. Which AI tools touch your code? Who owns their permission settings? How quickly do they apply security updates? Our AI-assisted development service builds those answers into the delivery plan. To scope a project, start here.