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.
Cite this page
CVE-2026-33068. CVEDatabase.com. Retrieved 1 May 2026. https://cvedatabase.com/cve/CVE-2026-33068
Use CWE-807, Anthropic vendor hub and Claude Code product page to widen CVE-2026-33068 into its surrounding weakness, vendor, and product context.
Compare it with CVE-2026-35022, CVE-2026-35020 and CVE-2026-35021 for nearby disclosures in the same product family.