v2.1.187
Why CEREBRO kept it
Claude sandbox credential isolation improves agent security boundaries
The text below is an automated extraction of the article at https://github.com/anthropics/claude-code/releases/tag/v2.1.187, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).
<h2>What's changed</h2> <ul> <li>Added <code>sandbox.credentials</code> setting to block sandboxed commands from reading credential files and secret environment variables</li> <li>Added org-configured model restrictions to the model picker, <code>--model</code>, <code>/model</code>, and <code>ANTHROPIC_MODEL</code>, with a "restricted by your organization's settings" message when a restricted model is selected</li> <li>Added mouse click support to select menus (permission prompts, <code>/model</code>, <code>/config</code>, etc.) in fullscreen mode</li> <li>Fixed <code>--resume</code> failing w
Backlinks
Appeared in 1 briefing