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.

CVSS v3 9.8 CRITICAL

9.8^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 3.9 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3	Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:*

History

No history.

Information

Published : 2025-12-03 19:15

Updated : 2025-12-05 16:29

NVD link : CVE-2025-66032

Mitre link : CVE-2025-66032

CVE.ORG link : CVE-2025-66032

JSON object : View

Products Affected

anthropic

claude_code

CWE

CWE-77

Improper Neutralization of Special Elements used in a Command ('Command Injection')

{"id": "CVE-2025-66032", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 9.8, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 3.9}], "cvssMetricV40": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 8.7, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "HIGH", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "PASSIVE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "HIGH", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "HIGH", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "published": "2025-12-03T19:15:57.527", "references": [{"url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3", "tags": ["Vendor Advisory"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-77"}]}], "descriptions": [{"lang": "en", "value": "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."}, {"lang": "es", "value": "Claude Code es una herramienta de codificaci\u00f3n ag\u00e9ntica. Versiones anteriores a la 1.0.93, debido a errores en el an\u00e1lisis de comandos de shell relacionados con $IFS y flags CLI cortos, era posible eludir la validaci\u00f3n de solo lectura de Claude Code y desencadenar la ejecuci\u00f3n de c\u00f3digo arbitrario. Explotar esto de forma fiable requiere la capacidad de a\u00f1adir contenido no confiable en una ventana de contexto de Claude Code. Esta vulnerabilidad est\u00e1 corregida en la 1.0.93."}], "lastModified": "2025-12-05T16:29:42.130", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:*", "vulnerable": true, "matchCriteriaId": "E73D014A-196B-4DDC-AE9D-56279B7BD89A", "versionEndExcluding": "1.0.93"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}