CVE-2026-55253

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

State
Published
Severity
7.7 High
Published
Sep 14, 2026
Updated
Sep 14, 2026
Reserved
Jun 16, 2026

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
3.17.7 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:NGitHub_M

Weaknesses

  • CWE-943 Improper Neutralization of Special Elements in Data Query Logic

Affected Products

ProductVersions
langchain-mongodblangchain-ai
  • < 0.4.0Affected
langgraph-checkpoint-mongodblangchain-ai
  • < 0.3.0Affected
langgraph-store-mongodblangchain-ai
  • < 0.4.0Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.