VDB
Sign up
HIGH

GHSA-mmgp-wc2j-qcv7

Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Quick fix

GHSA-mmgp-wc2j-qcv7 — @anthropic-ai/claude-code: upgrade to the fixed version with the command below.

npm install @anthropic-ai/claude-code@2.1.53

Details

Claude Code resolved the permission mode from settings files, including the repo-controlled `.claude/settings.json`, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set `permissions.defaultMode` to `bypassPermissions` in its committed `.claude/settings.json`, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent.

Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.

Thank you to hackerone.com/cantina_xyz for reporting this issue.

Are you affected?

Enter the version of the package you're using.

Affected packages

npm/@anthropic-ai/claude-code
Introduced in: 0Fixed in: 2.1.53
Fixnpm install @anthropic-ai/claude-code@2.1.53

References