Vulnerability · Published Aug 4, 2026 · Assigned by GitHub_M
CVE-2026-48121@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access
Medium 6.7
In plain English
A medium-severity security flaw in langgraphjs from langchain-ai. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 29% of all known vulnerabilities). Ready-made attack tooling exists: public proof-of-concept code. Fixed versions are available - upgrade the affected package.
Official description
@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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| npm | @langchain/langgraph-checkpoint-mongodb | 1.3.1 | GHSA-98xf-r82g-9mhx |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| langchain-ai | langgraphjs | < 1.3.1 |
Weakness: CWE-943 · Vector: CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N