Claude Code 2.1.325 tightens sandbox and permission rules and fixes a security flaw

Claude Code 2.1.325 fixes a security issue in decoding compressed responses and changes sandboxed commands to follow the normal permission flow by default. AI coding tool security settings are shifting under teams' feet.

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

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.

← All research

More research.

GitHub Copilot adds Supabase, Webflow, Wix and five more connectors in public preview

GitHub Copilot now connects to eight more services, including Supabase, Webflow, Wix and Mixpanel, through verified MCP connectors in public preview. They join more than 25 existing ones.

Read ›

Gemini 4 Neon is generally available in GitHub Copilot, aimed at lower-cost agentic coding

Gemini 4 Neon is now generally available in GitHub Copilot for agentic coding. Google says its quality is close to Gemini 4 Carbon at a lower token cost per task.

Read ›

Claude Code 2.1.328 brings auto mode to Bedrock, Vertex and Foundry, and narrows /code-review to bugs

Claude Code 2.1.328 extends auto mode to Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud and Microsoft Foundry. /code-review now reports only bugs and CLAUDE.md violations.

Read ›

GitHub Copilot Evals: repeatable tests for AI agents, now in public preview

GitHub Copilot Evals lets teams write repeatable tests for AI coding skills, custom agents and MCP tools. It checks both the result and the path the agent took, and is in public preview.

Read ›

GitHub Copilot can now drive your browser: browser use enters public preview

GitHub Copilot browser use lets an AI coding agent control Chrome to debug web apps and run browser tests. It is in public preview across the CLI, the Copilot app, VS Code and JetBrains.

Read ›

Claude Code 2.1.327 refuses some symbolic links and lists broken setup in /status

Claude Code 2.1.327 tightens file and package permissions again and adds a /status list of broken agent, skill and hook settings. A short read for teams using AI coding tools on a live product.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work