CVE-2026-48121

@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1.

CVSS v3 6.7 MEDIUM

6.7^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 1.5 / Impact : 5.2

Attack Vector ADJACENT_NETWORK

Attack Complexity LOW

Privileges Required LOW

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact NONE

Scope UNCHANGED

References

Link	Resource
https://github.com/langchain-ai/langgraphjs/commit/284226c7ca164b3c81fe2d9e32b10f1fc6b99a3c
https://github.com/langchain-ai/langgraphjs/issues/2351
https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-98xf-r82g-9mhx

Configurations

No configuration.

History

No history.

Information

Published : 2026-08-04 17:16

Updated : 2026-09-09 20:50

NVD link : CVE-2026-48121

Mitre link : CVE-2026-48121

CVE.ORG link : CVE-2026-48121

JSON object : View

Products Affected

No product.

CWE

CWE-943

Improper Neutralization of Special Elements in Data Query Logic

{"id": "CVE-2026-48121", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-48121", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-08-04T19:15:56.587064Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 6.7, "attackVector": "ADJACENT_NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 5.2, "exploitabilityScore": 1.5}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "langchain-ai", "product": "langgraphjs", "versions": [{"status": "affected", "version": "< 1.3.1"}]}]}], "published": "2026-08-04T17:16:55.267", "references": [{"url": "https://github.com/langchain-ai/langgraphjs/commit/284226c7ca164b3c81fe2d9e32b10f1fc6b99a3c", "source": "security-advisories@github.com"}, {"url": "https://github.com/langchain-ai/langgraphjs/issues/2351", "source": "security-advisories@github.com"}, {"url": "https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-98xf-r82g-9mhx", "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/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1."}], "lastModified": "2026-09-09T20:50:00.950", "sourceIdentifier": "security-advisories@github.com"}