CVE-2026-55253
LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0, MongoDBSaver.list(), MongoDBSaver.alist(), and MongoDBStore.search() incorporate filter dictionaries into MongoDB queries without recursively rejecting keys prefixed with $. An authenticated caller who controls a filter argument through HTTP query parameters, request body fields, or agent tool arguments can inject MongoDB Query Language operators such as $regex or $where.
Leer descripción completaMostrar menos
In a multi-tenant deployment that uses the filter to enforce per-user or per-tenant isolation, injected operators can bypass intended equality filtering and expose other tenants' checkpoint or store data. Filters constructed entirely from trusted server-side values have lower practical risk. This issue is fixed in langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0.
CVSS
- Versión: 3.1
- Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
- Puntuación base: 7.7
Probabilidad de explotación (EPSS)
- Probabilidad de explotación en los próximos 30 días: 0.53%
- Percentil entre todas las CVEs puntuadas: 43
- 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
T1210Exploitation of Remote Serviceslateral movement85 % - Impacto principal
T1005Data from Local Systemcollection90 % - Impacto secundario
T1078.004Cloud Accountsstealth · persistence · privilege escalation · initial access75 %
Inyección MongoDB por usuario autenticado (PR:L) en servicio remoto. Permite leer datos de otros tenants (T1005) y potencialmente eludir controles de aislamiento de cuentas (T1078.004).
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 (2)
⚠ Inferidas por IA a partir de la descripción — NVD aún no ha analizado esta CVE; no son CPE verificados.
CWE
- CWE-943
Referencias
- https://github.com/langchain-ai/langchain-mongodb/commit/14a6cc39e67d23fd409cd13a9caae2c329df0a09
- https://github.com/langchain-ai/langchain-mongodb/commit/240e7ecee432ea006d9fef6ea506bfd2e009a3f4
- https://github.com/langchain-ai/langchain-mongodb/commit/5465e4d3ea0ef5c88a666a6442bd853ff4bd70e5
- https://github.com/langchain-ai/langchain-mongodb/pull/384
- https://github.com/langchain-ai/langchain-mongodb/releases/tag/libs/langgraph-checkpoint-mongodb/v0.4.0
- https://github.com/langchain-ai/langchain-mongodb/releases/tag/libs/langgraph-store-mongodb/v0.3.0
- https://github.com/langchain-ai/langchain-mongodb/security/advisories/GHSA-533j-2v4q-mw5h
JSON original (NVD)
Mostrar
{
"id": "CVE-2026-55253",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-55253",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"version": "2.0.3",
"timestamp": "2026-09-14T19:20:51.424583Z"
}
}
],
"cvssMetricV31": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"cvssData": {
"scope": "CHANGED",
"version": "3.1",
"baseScore": 7.7,
"attackVector": "NETWORK",
"baseSeverity": "HIGH",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N",
"integrityImpact": "NONE",
"userInteraction": "NONE",
"attackComplexity": "LOW",
"availabilityImpact": "NONE",
"privilegesRequired": "LOW",
"confidentialityImpact": "HIGH"
},
"impactScore": 4,
"exploitabilityScore": 3.1
}
]
},
"affected": [
{
"source": "security-advisories@github.com",
"affectedData": [
{
"vendor": "langchain-ai",
"product": "langchain-mongodb",
"versions": [
{
"status": "affected",
"version": "< 0.4.0"
}
]
},
{
"vendor": "langchain-ai",
"product": "langgraph-checkpoint-mongodb",
"versions": [
{
"status": "affected",
"version": "< 0.3.0"
}
]
},
{
"vendor": "langchain-ai",
"product": "langgraph-store-mongodb",
"versions": [
{
"status": "affected",
"version": "< 0.4.0"
}
]
}
]
}
],
"published": "2026-09-14T18:17:55.500",
"references": [
{
"url": "https://github.com/langchain-ai/langchain-mongodb/commit/14a6cc39e67d23fd409cd13a9caae2c329df0a09",
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/langchain-ai/langchain-mongodb/commit/240e7ecee432ea006d9fef6ea506bfd2e009a3f4",
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/langchain-ai/langchain-mongodb/commit/5465e4d3ea0ef5c88a666a6442bd853ff4bd70e5",
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/langchain-ai/langchain-mongodb/pull/384",
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/langchain-ai/langchain-mongodb/releases/tag/libs/langgraph-checkpoint-mongodb/v0.4.0",
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/langchain-ai/langchain-mongodb/releases/tag/libs/langgraph-store-mongodb/v0.3.0",
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/langchain-ai/langchain-mongodb/security/advisories/GHSA-533j-2v4q-mw5h",
"source": "security-advisories@github.com"
}
],
"vulnStatus": "Awaiting Analysis",
"weaknesses": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"description": [
{
"lang": "en",
"value": "CWE-943"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0, MongoDBSaver.list(), MongoDBSaver.alist(), and MongoDBStore.search() incorporate filter dictionaries into MongoDB queries without recursively rejecting keys prefixed with $. An authenticated caller who controls a filter argument through HTTP query parameters, request body fields, or agent tool arguments can inject MongoDB Query Language operators such as $regex or $where. In a multi-tenant deployment that uses the filter to enforce per-user or per-tenant isolation, injected operators can bypass intended equality filtering and expose other tenants' checkpoint or store data. Filters constructed entirely from trusted server-side values have lower practical risk. This issue is fixed in langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0."
}
],
"lastModified": "2026-09-30T17:43:24.057",
"sourceIdentifier": "security-advisories@github.com"
}