Vulnerability in Langchain-Ai Langgraphjs

CVE-2026-48121

@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.

EPSS: 0.002 (14.0th percentile) — read the EPSS interpretation.

CVSS v3 metric

CVSS v3 base score 6.7 (Medium). Vector: CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N.

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-48121?
CVE-2026-48121 is a medium-severity vulnerability in Langchain-Ai Langgraphjs, classified under Improper Neutralization of Special Elements in Data Query Logic. CVSS score: 6.7/10. Published 2026-08-04.
How severe is CVE-2026-48121?
Medium severity. CVSS v3 base score is 6.7 out of 10.