CVE-2025-30202
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL interfaces. While the socket is always opened for a multi-node deployment, it is only used when doing tensor parallelism across multiple hosts.
Leer descripción completaMostrar menos
Any client with network access to this host can connect to this XPUB socket unless its port is blocked by a firewall. Once connected, these arbitrary clients will receive all of the same data broadcasted to all of the secondary vLLM hosts. This data is internal vLLM state information that is not useful to an attacker. By potentially connecting to this socket many times and not reading data published to them, an attacker can also cause a denial of service by slowing down or potentially blocking the publisher. This issue has been patched in version 0.8.5.
CVSS
- Versión: 3.1
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Puntuación base: 7.5
Probabilidad de explotación (EPSS)
- Probabilidad de explotación en los próximos 30 días: 0.60%
- Percentil entre todas las CVEs puntuadas: 47
- Fecha de la puntuación: 6/10/2026
EPSS (Exploit Prediction Scoring System, de FIRST) estima la probabilidad de que una vulnerabilidad sea explotada en 30 días. Complementa a CVSS (impacto) y a CISA KEV (explotación confirmada).
🎯 Técnicas ATT&CK
Cómo se explota esta vulnerabilidad y qué consigue el atacante, en el lenguaje de MITRE ATT&CK.
- Explotación
T1190Exploit Public-Facing Applicationinitial access85 % - Impacto principal
T1499.001OS Exhaustion Floodimpact80 % - Impacto secundario
T1005Data from Local Systemcollection75 %
Vector AV:N/PR:N/UI:N indica acceso remoto sin privilegios: T1190. ZeroMQ XPUB socket expuesto permite DoS por conexiones simultáneas sin leer datos (T1499.001) y exposición de estado interno de vLLM (T1005).
Inferido por nuestro agente de análisis a partir de la descripción oficial, el vector CVSS y la CWE, y comprobado por un supervisor. Puede contener errores.
🛡️ Mitigaciones ATT&CK que cubren estas técnicas
Tecnologías afectadas (1)
CWE
- CWE-770
Referencias
JSON original (NVD)
Mostrar
{
"id": "CVE-2025-30202",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2025-30202",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "yes"
},
{
"technicalImpact": "partial"
}
],
"version": "2.0.3",
"timestamp": "2025-04-30T13:16:29.868734Z"
}
}
],
"cvssMetricV31": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"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
},
{
"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
}
]
},
"affected": [
{
"source": "security-advisories@github.com",
"affectedData": [
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"status": "affected",
"version": ">= 0.5.2, < 0.8.5"
}
]
}
]
}
],
"published": "2025-04-30T01:15:51.800",
"references": [
{
"url": "https://github.com/vllm-project/vllm/commit/a0304dc504c85f421d38ef47c64f83046a13641c",
"tags": [
"Patch"
],
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/vllm-project/vllm/pull/6183",
"tags": [
"Issue Tracking",
"Patch"
],
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-9f8f-2vmf-885j",
"tags": [
"Exploit",
"Vendor Advisory"
],
"source": "security-advisories@github.com"
}
],
"vulnStatus": "Analyzed",
"weaknesses": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"description": [
{
"lang": "en",
"value": "CWE-770"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL interfaces. While the socket is always opened for a multi-node deployment, it is only used when doing tensor parallelism across multiple hosts. Any client with network access to this host can connect to this XPUB socket unless its port is blocked by a firewall. Once connected, these arbitrary clients will receive all of the same data broadcasted to all of the secondary vLLM hosts. This data is internal vLLM state information that is not useful to an attacker. By potentially connecting to this socket many times and not reading data published to them, an attacker can also cause a denial of service by slowing down or potentially blocking the publisher. This issue has been patched in version 0.8.5."
},
{
"lang": "es",
"value": "vLLM es un motor de inferencia y servicio de alto rendimiento y eficiente en memoria para LLM. Las versiones a partir de la 0.5.2 y anteriores a la 0.8.5 son vulnerables a denegación de servicio y exposición de datos a través de ZeroMQ en implementaciones de vLLM multinodo. En una implementación de vLLM multinodo, vLLM utiliza ZeroMQ para algunos fines de comunicación multinodo. El host vLLM principal abre un socket XPUB ZeroMQ y lo vincula a TODAS las interfaces. Si bien el socket siempre está abierto para implementaciones multinodo, solo se utiliza al realizar paralelismo tensorial en varios hosts. Cualquier cliente con acceso de red a este host puede conectarse a este socket XPUB a menos que su puerto esté bloqueado por un firewall. Una vez conectados, estos clientes arbitrarios recibirán los mismos datos transmitidos a todos los hosts vLLM secundarios. Estos datos son información interna del estado de vLLM que no es útil para un atacante. Al conectarse a este socket muchas veces y no leer los datos publicados, un atacante también puede causar una denegación de servicio al ralentizar o incluso bloquear al publicador. Este problema se ha corregido en la versión 0.8.5."
}
],
"lastModified": "2026-06-17T09:08:20.873",
"configurations": [
{
"nodes": [
{
"negate": false,
"cpeMatch": [
{
"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"vulnerable": true,
"matchCriteriaId": "15AC3826-5B31-40E2-9964-6F8930043285",
"versionEndExcluding": "0.8.5",
"versionStartIncluding": "0.5.2"
}
],
"operator": "OR"
}
]
}
],
"sourceIdentifier": "security-advisories@github.com"
}