Brief
Claude Code v2.1.271 adds per-command allowed domains for sandboxed Bash, PowerShell, and Monitor
The release notes for Claude Code v2.1.271 include a change that lets each command in auto mode with sandboxing have its own allowed_domains, with other hosts refused. The notes are brief on configuration details.
In auto mode with sandboxing, Bash, PowerShell, and Monitor commands can now be assigned per-command allowed_domains. The hosts a command needs are reviewed with it and opened for it alone; other hosts are refused.
This changes a workflow step: instead of a blanket network policy, each command carries its own host allowlist. Operators will need to specify allowed domains per command, which could affect how scripts are written and reviewed.
Our reading
Our reading is that this shifts network access control from a global setting to a per-command configuration, requiring operators to declare allowed hosts for each command in sandboxed auto mode.
Source details and supporting facts
Each line is stated by the page named above it.
Stated by github.com
- Added per-command allowed_domains to Bash, PowerShell and Monitor in auto mode with sandboxing: the hosts a command needs are reviewed with it and opened for it alone; other hosts are refused
Sources
- Anthropic Claude Code release notes (GitHub)Text stored 15 September 2026
How this story was checked. Written from the 1 page listed above, stored 15 September 2026; claims checked against that stored text on 15 September 2026.
What that means
- 1 of 1 reported statements were confirmed against the page that carries them; the rest were removed rather than published.
- Figures in the text were required to appear in the stored source text: yes. Identifiers: yes.
- The check reads stored text only: no claim rests on a fresh look that did not happen.
- Where the reporting was silent, the text says so instead of filling the gap.