CVE-2026-100654
vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service).
CVSS
- Versión: 4.0
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/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
- Puntuación base: 7.1
Probabilidad de explotación (EPSS)
- Probabilidad de explotación en los próximos 30 días: 0.31%
- Percentil entre todas las CVEs puntuadas: 21
- 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
T1210Exploitation of Remote Serviceslateral movement85 % - Impacto principal
T1499.004Application or System Exploitationimpact90 %
Vulnerabilidad en servicio remoto (OpenAI API compatible) que requiere autenticación previa. El atacante autenticado envía parámetro malformado (stop_token_ids fuera de rango) causando assertion en CUDA, generando DoS por crash del servicio hasta reinicio.
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)
⚠ Inferidas por IA a partir de la descripción — NVD aún no ha analizado esta CVE; no son CPE verificados.
CWE
- CWE-129
Referencias
JSON original (NVD)
Mostrar
{
"id": "CVE-2026-100654",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-100654",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"version": "2.0.3",
"timestamp": "2026-09-30T14:51:29.949766Z"
}
}
],
"cvssMetricV31": [
{
"type": "Secondary",
"source": "disclosure@vulncheck.com",
"cvssData": {
"scope": "UNCHANGED",
"version": "3.1",
"baseScore": 6.5,
"attackVector": "NETWORK",
"baseSeverity": "MEDIUM",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
"integrityImpact": "NONE",
"userInteraction": "NONE",
"attackComplexity": "LOW",
"availabilityImpact": "HIGH",
"privilegesRequired": "LOW",
"confidentialityImpact": "NONE"
},
"impactScore": 3.6,
"exploitabilityScore": 2.8
}
],
"cvssMetricV40": [
{
"type": "Secondary",
"source": "disclosure@vulncheck.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:L/UI:N/VC:N/VI:N/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": "NONE",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"privilegesRequired": "LOW",
"subIntegrityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"vulnAvailabilityImpact": "HIGH",
"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-project",
"product": "vllm",
"versions": [
{
"status": "affected",
"version": "0",
"lessThan": "0.29.0",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "0.29.0",
"versionType": "semver"
}
],
"packageURL": "pkg:pypi/vllm",
"defaultStatus": "unaffected"
}
]
}
],
"published": "2026-09-26T14:16:48.100",
"references": [
{
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-v5gm-qgmv-gc6c",
"source": "disclosure@vulncheck.com"
},
{
"url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-out-of-range-stop-token-ids",
"source": "disclosure@vulncheck.com"
}
],
"vulnStatus": "Undergoing Analysis",
"weaknesses": [
{
"type": "Secondary",
"source": "disclosure@vulncheck.com",
"description": [
{
"lang": "en",
"value": "CWE-129"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service)."
}
],
"lastModified": "2026-09-30T15:22:15.250",
"sourceIdentifier": "disclosure@vulncheck.com"
}