GHSA-mmgp-wc2j-qcv7
Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File
Packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| npm | @anthropic-ai/claude-code | < 2.1.53 | 2.1.53 |
Details
As written in the advisory (Markdown source, shown as plain text).
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.
References
External links from the advisory. They lead to third-party sites.