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

published 2026-08-20 2 mo ago modified 2026-09-30 39 d ago also GHSA-533j-2v4q-mw5h , PYSEC-2026-3859 , PYSEC-2026-3860 , EUVD-2026-77674

cvss: 7.7; version 3.1, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 0.5%; EPSS 0.5% chance of exploitation in 30 days, percentile 45%
public exploits: 0; none known

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.

Patch / fix

fixed in 2 links 8

pypi langgraph-checkpoint-mongodb 0.3.0
pypi langgraph-store-mongodb 0.4.0

CISA SSVC

Exploitation: none
Automatable: no
Technical impact: partial
Assessed: 55 d ago (2026-09-14)

Exploit prediction

0.53% chance of exploitation in the next 30 days, higher than 45% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by	version	score	vector
CNA	3.1	7.7	CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
OSV	3.1	7.7	CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
GitHub	3.1	7.7	CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N

Affected packages

ecosystem	package	affected	fixed in
pypi	langgraph-checkpoint-mongodb	<0.3.0	0.3.0
pypi	langgraph-store-mongodb	<0.4.0	0.4.0

Affected products

langchain-ai langchain-mongodb
langchain-ai langgraph-checkpoint-mongodb
langchain-ai langgraph-store-mongodb

Classification

Weakness

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

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

Summary