CVE-2026-33068
Description
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.
How to fix
- anthropic claude_code2.1.53 or later
- @anthropic-ai/claude-code2.1.53 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| anthropic claude_code | v < 2.1.53 | 2.1.53 |
| @anthropic-ai/claude-codenpm | v < 2.1.53 | 2.1.53 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.