CVE-2026-55253
Received Received - Intake

Authentication Bypass in LangChain MongoDB Integration

Publication date: 2026-09-14

Last updated on: 2026-09-14

Assigner: GitHub, Inc.

Description
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.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-14
Last Modified
2026-09-14
Generated
2026-09-14
AI Q&A
2026-09-14
EPSS Evaluated
N/A
NVD
CVE-2026-55253
EUVD
EUVD-2026-77674

Affected Vendors & Products

Showing 4 associated CPEs
Vendor Product Version / Range
langchain langgraph-checkpoint-mongodb 0.3.0
langchain langgraph-store-mongodb 0.4.0
langchain-ai langgraph-checkpoint-mongodb to 0.3.0 (exc)
langchain-ai langgraph-store-mongodb to 0.4.0 (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-943 The product generates a query intended to access or manipulate data in a data store such as a database, but it does not neutralize or incorrectly neutralizes special elements that can modify the intended logic of the query.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability affects LangChain MongoDB integrations. It allows authenticated attackers to inject MongoDB Query Language operators like $regex or $where into filter dictionaries used in queries. This bypasses intended data isolation in multi-tenant deployments, potentially exposing other tenants' checkpoint or store data.

Detection Guidance

Check if your system uses langgraph-checkpoint-mongodb versions prior to 0.3.0 or langgraph-store-mongodb versions prior to 0.4.0. Inspect installed packages with commands like pip show langgraph-checkpoint-mongodb or pip show langgraph-store-mongodb.

Impact Analysis

If you use LangChain MongoDB in a multi-tenant setup, attackers could access other tenants' sensitive data by manipulating filter arguments. Even in single-tenant setups, unauthorized data exposure may occur if filters are user-controlled.

Compliance Impact

This vulnerability could lead to unauthorized data access, violating GDPR's data protection principles and HIPAA's security requirements for protected health information. Non-compliance risks include fines and legal penalties.

Mitigation Strategies

Upgrade langgraph-checkpoint-mongodb to version 0.3.0 or later and langgraph-store-mongodb to version 0.4.0 or later. Review and restrict user input in filter arguments to prevent injection of MongoDB operators like $regex or $where.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-55253. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart