AI and data stack advisories

Severe, 6 weeks1496Projects326

1496 severe, 6 weeks · 326 projects

AnthropicGHSA-mmgp-wc2j-qcv7

Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Anthropic

CVE-2026-33068 · Published Mar 18, 2026

High7.7
Fix: upgrade to 2.1.53 or later
GitHub advisory

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.

Affected versions

PackageAffectedFixed in
@anthropic-ai/claude-code
npm
< 2.1.532.1.53
Details and references
CVSS 4.0
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Severity from
GitHub (reviewed advisory)
Weakness
CWE-807

More Anthropic advisories

All Anthropic