CVE-2026-40068 Claude Code arbitrary code execution via git worktree commondir trust dialog bypass
Attackers can execute arbitrary code by bypassing trust dialogs via malicious git worktree configurations in Claude Code.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- A user has to click or open something
- Fix
- Available
What is CVE-2026-40068?
CVE-2026-40068 is a high-severity code injection vulnerability in anthropics claude-code, published on 5 May 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Official description
In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used the git worktree commondir file without validating its contents. An attacker could craft a malicious repository with a commondir file pointing to a path the victim had previously trusted, causing Claude Code to bypass its trust confirmation dialog and immediately execute hooks defined in `.claude/settings.json`. Exploitation requires the victim to clone the malicious repository and run Claude Code within it, and the attacker must know or guess a path the victim had already trusted. This issue has been fixed in version 2.1.84.
Which versions are affected by CVE-2026-40068?
2 open source packages ship an affected version, including @anthropic-ai/claude-code. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
@anthropic-ai/claude-code npm | From 2.1.63 | 2.1.84 |
@anthropic-ai/claude-code npm | From 2.1.63 | 2.1.84 |
Products include Anthropic Claude Code.
How do I fix CVE-2026-40068?
Upgrade @anthropic-ai/claude-code to 2.1.84 or later.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-40068 being exploited?
There is no known exploitation of CVE-2026-40068 in the wild and no public exploit code.
Other vulnerabilities in anthropics claude-code
- CVE-2025-66032 Claude Code Command Validation Bypass Allows Arbitrary Code Execution
- CVE-2025-64755 @anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes
- CVE-2025-59536 Claude Code's startup trust dialog could lead to Command Execution attack
- CVE-2025-58764 Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution
- CVE-2025-59041 Claude Code vulnerable to arbitrary code execution caused by maliciously configured git email
Sources
Also known as GHSA-q5hj-mxqh-vv77, MINI-79c8-vcm6-8w87, MINI-89f8-p2c9-3w6j.