CVE-2025-55284

Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update.

CVSS

No CVSS.

References

Link	Resource
https://github.com/anthropics/claude-code/security/advisories/GHSA-x5gv-jw7f-j6xj

Configurations

No configuration.

History

18 Aug 2025, 20:16

Type	Values Removed	Values Added
Summary		(es) Claude Code es una herramienta de codificación agentica. Antes de la versión 1.0.4, era posible omitir las solicitudes de confirmación de Claude Code para leer un archivo y luego enviar su contenido por la red sin la confirmación del usuario debido a una lista de comandos seguros demasiado amplia. Para explotar esto de forma fiable, es necesario poder añadir contenido no confiable a una ventana de contexto de Claude Code. Los usuarios con la actualización automática estándar de Claude Code recibieron esta corrección automáticamente tras el lanzamiento. Los usuarios actuales de Claude Code no se ven afectados, ya que las versiones anteriores a la 1.0.24 están obsoletas y se han visto obligados a actualizar.

16 Aug 2025, 02:15

Type	Values Removed	Values Added
New CVE

Information

Published : 2025-08-16 02:15

Updated : 2025-08-18 20:16

NVD link : CVE-2025-55284

Mitre link : CVE-2025-55284

CVE.ORG link : CVE-2025-55284

JSON object : View

Products Affected

No product.

CWE

CWE-78

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

{"id": "CVE-2025-55284", "cveTags": [], "metrics": {"cvssMetricV40": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 7.1, "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:N/VA:N/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": "NONE", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "NONE", "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": "2025-08-16T02:15:24.637", "references": [{"url": "https://github.com/anthropics/claude-code/security/advisories/GHSA-x5gv-jw7f-j6xj", "source": "security-advisories@github.com"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Primary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-78"}]}], "descriptions": [{"lang": "en", "value": "Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update."}, {"lang": "es", "value": "Claude Code es una herramienta de codificaci\u00f3n agentica. Antes de la versi\u00f3n 1.0.4, era posible omitir las solicitudes de confirmaci\u00f3n de Claude Code para leer un archivo y luego enviar su contenido por la red sin la confirmaci\u00f3n del usuario debido a una lista de comandos seguros demasiado amplia. Para explotar esto de forma fiable, es necesario poder a\u00f1adir contenido no confiable a una ventana de contexto de Claude Code. Los usuarios con la actualizaci\u00f3n autom\u00e1tica est\u00e1ndar de Claude Code recibieron esta correcci\u00f3n autom\u00e1ticamente tras el lanzamiento. Los usuarios actuales de Claude Code no se ven afectados, ya que las versiones anteriores a la 1.0.24 est\u00e1n obsoletas y se han visto obligados a actualizar."}], "lastModified": "2025-08-18T20:16:28.750", "sourceIdentifier": "security-advisories@github.com"}