CVE-2026-33068: Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Published Mar 19, 2026
·
Updated

Claude Code is an agentic coding tool. Versions prior to 2.1.53 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. This issue has been patched in version 2.1.53.

Other sources

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/cantinaxyz for reporting this issue.

— GitHub

Affected Software

2 affected componentsFixes available
npm/@anthropic-ai/claude-code<2.1.53
2.1.53
Anthropic Claude Code Node.js<2.1.53

Event History

Mar 19, 2026
Advisory Published
via GitHub·12:42 PM
Data Sourced
via GitHub·12:42 PM
DescriptionWeaknessAffected Software
Mar 20, 2026
CVE Published
via MITRE·08:17 AM
Data Sourced
via MITRE·08:17 AM
DescriptionWeakness
Data Sourced
via NVD·09:16 AM
DescriptionSeverityWeakness
Data Sourced
via NVD·09:16 AM
Affected Software
May 7, 2026
News Published
via Dark Reading·01:00 PM
May 12, 2026
News Published
via Dark Reading·01:07 PM
Free Weekly Intel

Don't miss critical vulnerabilities

Join thousands of security professionals who receive our weekly digest of trending CVEs, zero-days, and exploited vulnerabilities.

No spam. Unsubscribe anytime.

Frequently Asked Questions

1

What is the severity of CVE-2026-33068?

CVE-2026-33068 is considered a high severity vulnerability due to the potential for privilege escalation.

2

How do I fix CVE-2026-33068?

To fix CVE-2026-33068, upgrade to version 2.1.53 or later of the @anthropic-ai/claude-code package.

3

What kind of exploits can occur due to CVE-2026-33068?

Exploiting CVE-2026-33068 could allow a malicious repository to bypass permission checks and execute unauthorized actions.

4

Which versions of @anthropic-ai/claude-code are affected by CVE-2026-33068?

All versions of @anthropic-ai/claude-code prior to 2.1.53 are affected by CVE-2026-33068.

5

Is CVE-2026-33068 related to workspace trust features?

Yes, CVE-2026-33068 specifically impacts the workspace trust confirmation dialog related to permission settings.

Company

Resources

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203
CVE-2026-33068 - Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File - SecAlerts