@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access

published 2026-06-12 4 mo ago modified 2026-10-24 15 d ago also GHSA-98xf-r82g-9mhx , EUVD-2026-52793

cvss: 6.7; version 3.1, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 0.3%; EPSS 0.3% chance of exploitation in 30 days, percentile 24%
public exploits: 0; none known

@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1.

Patch / fix

fixed in 1 links 2

npm @langchain/langgraph-checkpoint-mongodb 1.3.1

github.com/langchain-ai/langgraphjs@284226c commit
github.com/langchain-ai/langgraphjs#2397 pull request

CISA SSVC

Exploitation: none
Automatable: no
Technical impact: total
Assessed: 3 mo ago (2026-08-04)

Exploit prediction

0.31% chance of exploitation in the next 30 days, higher than 24% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by	version	score	vector
CNA	3.1	6.7	CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
GitHub	3.1	6.7	CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N

Affected packages

ecosystem	package	affected	fixed in
npm	@langchain/langgraph-checkpoint-mongodb	<1.3.1	1.3.1

Affected products

langchain-ai langgraphjs

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