What is the CVSS score of CVE-2025-66032?

CVE-2025-66032 has a CVSS 3.1 base score of 9.8 (Critical). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.1%.

Which versions of Claude Code are affected by CVE-2025-66032?

Claude Code versions prior to 1.0.93 contain a critical vulnerability (CVSS 9.8) that allows attackers to execute arbitrary code by injecting malicious content into the tool's context.. A patch is available.

Is there a public PoC exploit available for CVE-2025-66032?

Yes, a public proof-of-concept exploit is available for CVE-2025-66032. Prioritise patching immediately. EPSS: 0.1%.

How to fix or mitigate CVE-2025-66032?

Within 24 hours: Inventory all Claude Code deployments and identify instances processing external or user-supplied content. Within 7 days: Immediately upgrade to Claude Code version 1.0.93 or later across all systems; if upgrading is not possible, disable Claude Code functionality pending patch availability. Within 30 days: Conduct a security audit of Claude Code usage patterns and implement input validation controls to prevent future similar vulnerabilities.

Claude Code CVE-2025-66032

EUVD-2025-201016 CRITICAL

Command Injection (CWE-77)

2025-12-03 security-advisories@github.com

GHSA-xq4m-mc3c-vvg3

RCE Command Injection Claude Code Anthropic

9.8

CVSS 3.1 · GitHub Advisory

Severity by source

GitHub Advisory PRIMARY

9.8 CRITICAL

AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Patch released

Mar 31, 2026 - 21:13 nvd

Patch available

EUVD ID Assigned

Mar 15, 2026 - 16:14 euvd

EUVD-2025-201016

Analysis Generated

Mar 15, 2026 - 16:14 vuln.today

CVE Published

Dec 03, 2025 - 19:15 nvd

CRITICAL 9.8

DescriptionGitHub Advisory

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.

Analysis

Technical ContextAI

Command injection allows an attacker to execute arbitrary OS commands on the host system through a vulnerable application that passes user input to system shells.

RemediationAI

Avoid passing user input to system commands. Use language-specific APIs instead of shell commands. If unavoidable, use strict input validation and escaping.