CVE-2026-33068

The record

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.

Affected packages

Related vulnerabilities

• GHSA-mmgp-wc2j-qcv7 Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File Same vulnerability
• CVE-2026-54316 Claude Code is an agentic coding tool. Also affects @anthropic-ai/claude-code
• GHSA-fg94-h982-f3mm Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch Also affects @anthropic-ai/claude-code
• CVE-2026-40068 In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic… Also affects @anthropic-ai/claude-code
• GHSA-q5hj-mxqh-vv77 Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution Also affects @anthropic-ai/claude-code
• GHSA-vp62-r36r-9xqp Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside… Also affects @anthropic-ai/claude-code
• CVE-2026-39861 Claude Code is an agentic coding tool. Also affects @anthropic-ai/claude-code
• GHSA-5cwg-9f6j-9jvx Claude Code: Insecure System-Wide Configuration Loading Enables Local Privilege… Also affects @anthropic-ai/claude-code