Skip to content
CVE PROGRAM SOURCE RECORD7.7 High

CVE-2026-55253

LangChain MongoDB: NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant data exposure

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.

Affected products

Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.

langchain-ai langchain-mongodb

  • < 0.4.0affected

langchain-ai langgraph-checkpoint-mongodb

  • < 0.3.0affected

langchain-ai langgraph-store-mongodb

  • < 0.4.0affected

References