@anthropic-ai/claude-code
Affected
- introduced
0, fixed2.1.53(semver)
Fixed versions
2.1.53
Fix
- Fixed version
2.1.53npm install @anthropic-ai/[email protected]
Advisory
Also known as: 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. 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.
High Basis: The source's own band: HIGH
0, fixed 2.1.53 (semver)2.1.53
2.1.53npm install @anthropic-ai/[email protected]Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0