CVE-2025-66032

CRITICAL

9.8

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.

CVE Details

CVSS v3.1 Score9.8

SeverityCRITICAL

CVSS VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionNONE

Published12/3/2025

Last Modified12/5/2025

Sourcenvd

Honeypot Sightings0

Affected Products

anthropic:claude_code

Weaknesses (CWE)

CWE-77

References

https://github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.