Claude Code adds sandbox.credentials setting and model restrictions
TL;DR
Claude Code adds a sandbox.credentials setting to block sandboxed commands from reading secrets and integrates org-configured model restrictions. Mouse click support is added in fullscreen menus.
What changed
Claude Code added a sandbox.credentials setting to stop sandboxed commands from reading secrets along with org-configured model restrictions. Mouse click support was also added to fullscreen menus. Developers, Vibe Builders, and Basic Users now see these controls in their daily sessions.
Why it matters
Vibe Builders can keep creative projects secure without exposing keys during sandbox runs while Developers apply org model limits similar to how GitHub Copilot teams restrict options in shared workspaces. Basic Users gain simpler menu navigation that reduces friction on repeated tasks.
What to watch for
Compare the new sandbox setting against Cursor when testing command isolation and verify by running a sample command with the credentials flag enabled to confirm secret blocking.
Who this matters for
- Vibe Builders: Enable sandbox.credentials to prevent your creative scripts from accessing sensitive API keys.
Harsh’s take
Claude Code is maturing from a raw terminal experiment into a governed enterprise tool. The addition of sandbox credential blocking is a direct response to the security risks of letting an agentic CLI run arbitrary commands. It mirrors the permission structures we see in mature IDEs like Cursor or VS Code.
For operators, this update signals that Anthropic is prioritizing the safety of agentic workflows over pure speed. By integrating organizational model restrictions, they are making it easier for teams to manage costs and compliance without manual oversight. The mouse support in fullscreen menus is a small but necessary UX fix that makes the tool accessible to those who are not terminal purists.
by Harsh Desai
About Claude Code
View the full Claude Code page →All Claude Code updatesGo deeper
More AI news
- Weekly DigestHermes Agent A2A protocol and voice barge-in, OpenClaw Wear OS app, and open agent tool fixes you can test now
Hermes Agent rolled out dozens of reliability, voice, and multi-agent features while OpenClaw added session rewinding, state recovery, and Wear OS support across the week.
- Daily RoundupBigBang-v1 trends on Hugging Face, Seedance 2.5 on Fal, and agent tools on Product Hunt
New image-text models and consistent video generators arrived alongside browser agents and storage tools, while a major chip investment signals hardware momentum for builders shipping AI products.
- Daily RoundupFirebird AI Factory launch, Vercel on Hermes, and Replicate dubbing tools
Infrastructure scale-ups and agent tooling updates arrived on 8 August, with Firebird opening a major GPU site, Vercel integrations for Hermes, trending video models on Hugging Face, and fresh Replicate releases for filtering and translation.