CVEs / CVE-2026-55253
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. 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 · 2
| Product | Versions affected | Fixed in |
|---|---|---|
| LangChain | not stated by CPE | — |
| LangGraph | not stated by CPE | — |
Versions as NVD's CPE configuration states them; "—" means the record gives no fixed version, not that none exists. Check the vendor's advisory in the references.
In this registry
- LangChain — agent dossier
- LangChain Deep Agents — agent dossier
- LangGraph — agent dossier
References · 7
- github.com/langchain-ai/langchain-mongodb/commit/14a6cc39e67d23fd409cd13a9caae2c329df0a09
- github.com/langchain-ai/langchain-mongodb/commit/240e7ecee432ea006d9fef6ea506bfd2e009a3f4
- github.com/langchain-ai/langchain-mongodb/commit/5465e4d3ea0ef5c88a666a6442bd853ff4bd70e5
- github.com/langchain-ai/langchain-mongodb/pull/384
- github.com/langchain-ai/langchain-mongodb/releases/tag/libs/langgraph-checkpoint-mongodb/v
- github.com/langchain-ai/langchain-mongodb/releases/tag/libs/langgraph-store-mongodb/v0.3.0
- github.com/langchain-ai/langchain-mongodb/security/advisories/GHSA-533j-2v4q-mw5h
The official record's references, as NVD lists them, minus any tagged Exploit. Nothing here is an exploit or a proof of concept.
Description, scores, versions and references are the official CVE record's own, retrieved 2026-10-25 from NVD. Category, attack surface and cross-links are this registry's classification and can be wrong — use the button above. Not a severity assessment for your deployment.