CVE-2025-71379

vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service.

CVSS v3 4.3 MEDIUM

4.3^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 2.8 / Impact : 1.4

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required LOW

User Interaction NONE

Confidentiality Impact NONE

Integrity Impact NONE

Availability Impact LOW

Scope UNCHANGED

References

Link	Resource
https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhp	Exploit Vendor Advisory
https://www.vulncheck.com/advisories/vllm-regular-expression-denial-of-service-in-multiple-components	Third Party Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

05 Oct 2026, 16:10

Type	Values Removed	Values Added
Summary		(es) Las versiones de vLLM >= 0.6.3 y < 0.9.0 contienen múltiples vulnerabilidades de denegación de servicio por expresiones regulares (ReDoS). Varios patrones de expresiones regulares - en vllm/lora/utils.py, el analizador de herramientas phi4mini y el endpoint de chat de servicio compatible con OpenAI - son susceptibles a retrocesos catastróficos. Un atacante que envía una entrada manipulada con estructuras anidadas o repetidas puede desencadenar un consumo severo de CPU y una degradación del rendimiento, lo que resulta en una denegación de servicio.

Information

Published : 2026-06-20 19:16

Updated : 2026-10-12 22:10

NVD link : CVE-2025-71379

Mitre link : CVE-2025-71379

CVE.ORG link : CVE-2025-71379

JSON object : View

Products Affected

vllm

vllm

CWE

CWE-1333

Inefficient Regular Expression Complexity

{"id": "CVE-2025-71379", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2025-71379", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-06-22T17:54:20.295719Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 4.3, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "LOW", "privilegesRequired": "LOW", "confidentialityImpact": "NONE"}, "impactScore": 1.4, "exploitabilityScore": 2.8}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 7.5, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "NONE"}, "impactScore": 3.6, "exploitabilityScore": 3.9}], "cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 5.3, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/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": "NONE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "LOW", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "NONE", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "LOW", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "NONE", "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"}}]}, "affected": [{"source": "disclosure@vulncheck.com", "affectedData": [{"vendor": "vllm", "product": "vllm", "versions": [{"status": "affected", "version": "0.6.3", "lessThan": "0.9.0", "versionType": "semver"}, {"status": "unaffected", "version": "0.9.0", "versionType": "semver"}], "packageURL": "pkg:pypi/vllm", "defaultStatus": "unaffected"}]}], "published": "2026-06-20T19:16:23.410", "references": [{"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhp", "tags": ["Exploit", "Vendor Advisory"], "source": "disclosure@vulncheck.com"}, {"url": "https://www.vulncheck.com/advisories/vllm-regular-expression-denial-of-service-in-multiple-components", "tags": ["Third Party Advisory"], "source": "disclosure@vulncheck.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-1333"}]}], "descriptions": [{"lang": "en", "value": "vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns \u2014 in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint \u2014 are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service."}, {"lang": "es", "value": "Las versiones de vLLM >= 0.6.3 y < 0.9.0 contienen m\u00faltiples vulnerabilidades de denegaci\u00f3n de servicio por expresiones regulares (ReDoS). Varios patrones de expresiones regulares - en vllm/lora/utils.py, el analizador de herramientas phi4mini y el endpoint de chat de servicio compatible con OpenAI - son susceptibles a retrocesos catastr\u00f3ficos. Un atacante que env\u00eda una entrada manipulada con estructuras anidadas o repetidas puede desencadenar un consumo severo de CPU y una degradaci\u00f3n del rendimiento, lo que resulta en una denegaci\u00f3n de servicio."}], "lastModified": "2026-10-12T22:10:00.247", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "98236AEA-BBE9-4E78-A1CB-95E445D3ABE7", "versionEndExcluding": "0.9.0", "versionStartIncluding": "0.6.3"}], "operator": "OR"}]}], "sourceIdentifier": "disclosure@vulncheck.com"}