Security and data handling changedgovernment/security/security-and-data-handling
Upstream edited this page at 5 Nov 2026 15:29 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 5 Nov 2026 15:37 UTC.
Upstream edited
Recorded here
Lines+2added
Lines−2removed
From line
38
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits31to this page, all time
The whole hunk
from line 38, old and new numbered
/
from line 38
3838
3939Claude can also type commands into the Code tab's terminal, which is the user's own shell (PowerShell on Windows). The app asks the user to approve each of those commands by default, and they run as the user, outside any sandbox. Administrators can turn these terminal tools off with the **Terminal panel tools** card on the [Config](https://claude.com/docs/government/config/settings.md#tool-and-connector-cards) page. The [**Blocked shell commands**](https://claude.com/docs/government/config/settings.md#claude-code) list does not block commands Claude types into the terminal, but the **Require approval for each command** sub-setting on the **Shell commands** card applies to them in every permission mode.
4040
41On Linux, the sandbox requires the `bubblewrap` and `socat` packages, so install both on each workstation as described under [Set up Linux and WSL2](https://code.claude.com/docs/en/sandboxing#set-up-linux-and-wsl2) in the Claude Code documentation. If either package is missing, shell commands run outside the sandbox as they do on Windows.
41On Linux, the sandbox requires the `bubblewrap` and `socat` packages, so install both on each workstation as described under [Set up Linux and WSL2](https://code.claude.com/docs/en/sandboxing#set-up-linux-and-wsl2) in the Claude Code documentation. If either package is missing or the sandbox cannot start, shell commands can run outside it, as they do on Windows.
4242
4343On macOS and Linux, the sandbox also blocks connections to local Unix sockets. A command that talks to a local agent through a socket, such as git signing a commit with a key held in an SSH agent or a hardware-backed key manager, cannot reach that agent from inside the sandbox. On macOS, a user who needs such a command to work can list the agent's socket path under `sandbox.network.allowUnixSockets` in their Claude Code settings file, which keeps the command inside the sandbox. Every sandboxed command in that user's Code sessions can then ask the agent to sign or authenticate, so this is appropriate only for an agent that asks the user to approve each use, for example with Touch ID, and not for an agent that signs without prompting.
4444
from line 46
4646
4747Exempting git commands such as `git commit` with `sandbox.excludedCommands` is not a safe way around the socket restriction. A sandboxed command can still change files that git runs during a commit, such as hook scripts kept in the working tree, and an exempted `git commit` would then run that code outside the sandbox. On macOS, git also cannot reach remotes over SSH from inside the sandbox, so a user who needs to push can use an HTTPS remote whose host is on the **Allowed network hosts** list, or push from a terminal outside the Code session.
4848
49In container-based Linux environments, such as cloud development workspaces, the sandbox can fail to start, and shell commands in Code sessions then fail with a `bwrap` error. To run Code sessions there, turn off the **Shell command sandbox** switch under **Advanced settings** in the **Claude Code** section of the [Config](https://claude.com/docs/government/config/settings.md) page, at the level that applies to the members who work in those environments, such as a [directory group](https://claude.com/docs/government/config/overview.md#group-specific-settings).
49In container-based Linux environments, such as cloud development workspaces, the sandbox can fail to start, and shell commands in Code sessions can then fail with a `bwrap` error. To run Code sessions there, turn off the **Shell command sandbox** switch under **Advanced settings** in the **Claude Code** section of the [Config](https://claude.com/docs/government/config/settings.md) page, at the level that applies to the members who work in those environments, such as a [directory group](https://claude.com/docs/government/config/overview.md#group-specific-settings).
5050
5151The **Shell command sandbox** switch applies to those members on every device they use, not only in the container workspaces. It reaches their Code sessions where your organization's [Claude Code settings](https://claude.com/docs/government/config/settings.md#claude-code) do. Shell commands in those Code sessions then run without the sandbox, under the permission mode the user selects for the session, as they do on Windows, and the **Allowed network hosts** and **Allowed workspace folders** settings no longer confine what those commands can reach or change. The switch also turns the sandbox off in those members' sessions in the Claude Code command-line tool.
5252
No line in this hunk matches that.