CVE-2026-66007
Full vulnerability record from the local CVENow database.
Description
Datasets through 5.0.0, fixed in commit f989ef9, contains a path traversal vulnerability in folder-based dataset builders where the file_name metadata field is not properly validated before being joined to the dataset directory. Attackers can supply crafted file_name values with directory traversal sequences to read arbitrary local files, which are then embedded into output when save_to_disk or push_to_hub is called.
Severity
MEDIUM
CVSS score
6.9
(v4.0)
Vulnerability status
Analyzed
Source identifier
Published
2026-07-24 15:19:07.493000
Last modified
2026-10-24 13:10:00.147000
View original CVE JSON
{
"id": "CVE-2026-66007",
"sourceIdentifier": "[email protected]",
"published": "2026-07-24T15:19:07.493",
"lastModified": "2026-10-24T13:10:00.147",
"vulnStatus": "Analyzed",
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "Datasets through 5.0.0, fixed in commit f989ef9, contains a path traversal vulnerability in folder-based dataset builders where the file_name metadata field is not properly validated before being joined to the dataset directory. Attackers can supply crafted file_name values with directory traversal sequences to read arbitrary local files, which are then embedded into output when save_to_disk or push_to_hub is called."
},
{
"lang": "es",
"value": "Los conjuntos de datos hasta la versión 5.0.0, corregido en el commit f989ef9, contienen una vulnerabilidad de salto de ruta en los constructores de conjuntos de datos basados en carpetas, donde el campo de metadatos file_name no se valida correctamente antes de ser unido al directorio del conjunto de datos. Los atacantes pueden proporcionar valores file_name manipulados con secuencias de salto de directorio para leer archivos locales arbitrarios, los cuales son luego incrustados en la salida cuando se llama a save_to_disk o push_to_hub."
}
],
"affected": [
{
"source": "[email protected]",
"affectedData": [
{
"vendor": "huggingface",
"product": "datasets",
"defaultStatus": "unaffected",
"repo": "https://github.com/huggingface/datasets",
"packageURL": "pkg:pypi/datasets",
"versions": [
{
"version": "0",
"lessThanOrEqual": "5.0.0",
"versionType": "semver",
"status": "affected"
},
{
"version": "f989ef9b4cc6c0039a7a82458eebca49e2b58b4b",
"versionType": "git",
"status": "unaffected"
}
]
}
]
}
],
"metrics": {
"cvssMetricV40": [
{
"source": "[email protected]",
"type": "Secondary",
"cvssData": {
"version": "4.0",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/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",
"baseScore": 6.9,
"baseSeverity": "MEDIUM",
"attackVector": "NETWORK",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"privilegesRequired": "NONE",
"userInteraction": "ACTIVE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "NONE",
"vulnAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"subAvailabilityImpact": "NONE",
"exploitMaturity": "NOT_DEFINED",
"confidentialityRequirement": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"availabilityRequirement": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"valueDensity": "NOT_DEFINED",
"vulnerabilityResponseEffort": "NOT_DEFINED",
"providerUrgency": "NOT_DEFINED"
}
}
],
"cvssMetricV31": [
{
"source": "[email protected]",
"type": "Secondary",
"cvssData": {
"version": "3.1",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"attackVector": "NETWORK",
"attackComplexity": "LOW",
"privilegesRequired": "NONE",
"userInteraction": "REQUIRED",
"scope": "UNCHANGED",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"availabilityImpact": "NONE"
},
"exploitabilityScore": 2.8,
"impactScore": 3.6
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"timestamp": "2026-07-24T15:18:39.129173Z",
"id": "CVE-2026-66007",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"version": "2.0.3"
}
}
]
},
"weaknesses": [
{
"source": "[email protected]",
"type": "Secondary",
"description": [
{
"lang": "en",
"value": "CWE-22"
}
]
}
],
"configurations": [
{
"nodes": [
{
"operator": "OR",
"negate": false,
"cpeMatch": [
{
"vulnerable": true,
"criteria": "cpe:2.3:a:huggingface:datasets:*:*:*:*:*:python:*:*",
"versionEndIncluding": "5.0.0",
"matchCriteriaId": "916D9ACC-09C6-4CE3-AF31-34AB3C83A6AA"
}
]
}
]
}
],
"references": [
{
"url": "https://github.com/huggingface/datasets/commit/f989ef9b4cc6c0039a7a82458eebca49e2b58b4b",
"source": "[email protected]",
"tags": [
"Patch"
]
},
{
"url": "https://github.com/huggingface/datasets/issues/8324",
"source": "[email protected]",
"tags": [
"Exploit",
"Issue Tracking",
"Vendor Advisory"
]
},
{
"url": "https://github.com/huggingface/datasets/pull/8325",
"source": "[email protected]",
"tags": [
"Issue Tracking",
"Patch"
]
},
{
"url": "https://www.vulncheck.com/advisories/datasets-path-traversal-via-unsanitized-file-name-metadata",
"source": "[email protected]",
"tags": [
"Exploit",
"Patch",
"Third Party Advisory"
]
}
]
}