CVE-2025-66032 Claude Code Command Validation Bypass Allows Arbitrary Code Execution
Attackers can bypass read-only validation to execute arbitrary code by injecting malicious shell commands into the context window.
- 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-2025-66032?
CVE-2025-66032 is a high-severity command injection vulnerability in anthropics claude-code, published on 3 Dec 2025. 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
Claude Code is an agentic coding tool. Prior to 1.0.93, Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 1.0.93.
Weakness: CWE-77
Which versions are affected by CVE-2025-66032?
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 | All versions | 1.0.93 |
@anthropic-ai/claude-code npm | All versions | 1.0.93 |
Products include Anthropic Claude Code.
How do I fix CVE-2025-66032?
Upgrade @anthropic-ai/claude-code to 1.0.93 or later.
Upgrade, and pass arguments to programs as a list instead of through a shell. More about Command injection.
Is CVE-2025-66032 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-66032 exists.
Other vulnerabilities in anthropics claude-code
- 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
- CVE-2025-54795 Claude Code echo command allowed bypass of user approval prompt for command execution
Sources
Also known as GHSA-xq4m-mc3c-vvg3.