CVE-2026-33068: Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File
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.
What it is
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.
How to check
- Affected: @anthropic-ai/claude-code (npm) < 2.1.53.
- Compare your installed version with the range above (command below).
How to fix
- Upgrade @anthropic-ai/claude-code to 2.1.53 or later.
npm ls @anthropic-ai/claude-code -g # or: claude --versionSources
- criticalCVE-2026-96620: Claude Agent SDK (Python) resume option lets attackers run commands
- criticalUpGuard: 16,326 Supabase databases had readable tables
- highCVE-2026-86063: Claude Code: Plugin Hash Pin Bypass Allows Bypass of Hash Pinning
- highCVE-2026-103435: Claude Code could be raced into writing files outside the project