CVE-2025-66032

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.
Command Injection
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTNIST
9.8 CRITICAL
NETWORK
LOW
NONE
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub_MCNA
---
---
CISA-ADPADP
---
---
Base Score
CVSS 3.x
EPSS Score
Percentile: 36%
VendorProductVersion
anthropicclaude_code
𝑥
< 1.0.93
𝑥
= Vulnerable software versions
Common Weakness Enumeration
References
https://github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3