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
UNKNOWN
---
GitHub_MCNA
---
---
CISA-ADPADP
---
---
Awaiting analysis
This vulnerability is currently awaiting analysis.
Base Score
CVSS 3.x
EPSS Score
Percentile: Unknown
Common Weakness Enumeration
References
https://github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3