CVE-2026-7482
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer.
Leer descripción completaMostrar menos
The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).
CVSS
- Versión: 4.0
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/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:Y/R:A/V:D/RE:L/U:Red
- Puntuación base: 8.8
Probabilidad de explotación (EPSS)
- Probabilidad de explotación en los próximos 30 días: 0.71%
- Percentil entre todas las CVEs puntuadas: 52
- Fecha de la puntuación: 4/10/2026
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 access92 % - Impacto principal
T1005Data from Local Systemcollection95 % - Impacto secundario
T1552Unsecured Credentialscredential access90 %
Vector AV:N/PR:N permite ataque remoto sin autenticación contra endpoint /api/create expuesto. La lectura fuera de límites en el heap filtra datos sensibles (variables de entorno, claves API, datos de conversaciones) que pueden exfiltrarse vía /api/push a registro controlado por atacante.
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-125
Referencias
JSON original (NVD)
Mostrar
{
"id": "CVE-2026-7482",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-7482",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "yes"
},
{
"technicalImpact": "total"
}
],
"version": "2.0.3",
"timestamp": "2026-05-04T13:48:32.181054Z"
}
}
],
"cvssMetricV31": [
{
"type": "Secondary",
"source": "abd028dc-c042-4c4d-9749-38d0f850af89",
"cvssData": {
"scope": "UNCHANGED",
"version": "3.1",
"baseScore": 9.1,
"attackVector": "NETWORK",
"baseSeverity": "CRITICAL",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H",
"integrityImpact": "NONE",
"userInteraction": "NONE",
"attackComplexity": "LOW",
"availabilityImpact": "HIGH",
"privilegesRequired": "NONE",
"confidentialityImpact": "HIGH"
},
"impactScore": 5.2,
"exploitabilityScore": 3.9
}
],
"cvssMetricV40": [
{
"type": "Secondary",
"source": "abd028dc-c042-4c4d-9749-38d0f850af89",
"cvssData": {
"Safety": "NOT_DEFINED",
"version": "4.0",
"Recovery": "AUTOMATIC",
"baseScore": 8.8,
"Automatable": "YES",
"attackVector": "NETWORK",
"baseSeverity": "HIGH",
"valueDensity": "DIFFUSE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/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:Y/R:A/V:D/RE:L/U:Red",
"exploitMaturity": "NOT_DEFINED",
"providerUrgency": "RED",
"userInteraction": "NONE",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"privilegesRequired": "NONE",
"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": "HIGH",
"confidentialityRequirement": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"vulnerabilityResponseEffort": "LOW",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED"
}
}
]
},
"affected": [
{
"source": "abd028dc-c042-4c4d-9749-38d0f850af89",
"affectedData": [
{
"repo": "https://github.com/ollama/ollama",
"vendor": "ollama",
"product": "ollama",
"versions": [
{
"status": "affected",
"version": "0",
"lessThan": "0.17.1",
"versionType": "semver"
}
],
"packageName": "ollama/ollama",
"programFiles": [
"fs/ggml/gguf.go",
"server/quantization.go"
],
"collectionURL": "https://github.com",
"defaultStatus": "unaffected"
}
]
}
],
"published": "2026-05-04T13:16:01.727",
"references": [
{
"url": "https://github.com/ollama/ollama/commit/88d57d0483cca907e0b23a968c83627a20b21047",
"tags": [
"Patch"
],
"source": "abd028dc-c042-4c4d-9749-38d0f850af89"
},
{
"url": "https://github.com/ollama/ollama/pull/14406",
"tags": [
"Issue Tracking",
"Patch"
],
"source": "abd028dc-c042-4c4d-9749-38d0f850af89"
},
{
"url": "https://github.com/ollama/ollama/releases/tag/v0.17.1",
"tags": [
"Release Notes"
],
"source": "abd028dc-c042-4c4d-9749-38d0f850af89"
}
],
"vulnStatus": "Analyzed",
"weaknesses": [
{
"type": "Secondary",
"source": "abd028dc-c042-4c4d-9749-38d0f850af89",
"description": [
{
"lang": "en",
"value": "CWE-125"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed)."
}
],
"lastModified": "2026-06-17T11:02:30.040",
"configurations": [
{
"nodes": [
{
"negate": false,
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ollama:ollama:*:*:*:*:*:*:*:*",
"vulnerable": true,
"matchCriteriaId": "18CE34C3-1F67-46CE-8B8D-5B54FC3996EF",
"versionEndExcluding": "0.17.1"
}
],
"operator": "OR"
}
]
}
],
"sourceIdentifier": "abd028dc-c042-4c4d-9749-38d0f850af89"
}