PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-48121 langchain-ai CVE debrief

CVE-2026-48121 debrief based on the supplied source corpus. The CVE record was published on 2026-08-04T17:16:55.267Z. The @langchain/langgraph-checkpoint-mongodb package versions 1.3.0 and below are vulnerable to NoSQL injection due to lack of type enforcement on checkpoint identifiers passed into MongoDB find() queries. This could lead to potential leakage of checkpoints and bypassing of thread scoping. Defenders of applications using @langchain/langgraph-checkpoint-mongodb versions 1.3.0 and below, especially in multi-tenant or user-isolated setups, should assess exposure and prioritize verification and remediation.

Vendor
langchain-ai
Product
langgraphjs
CVSS
MEDIUM 6.7
CISA KEV
Not listed in stored evidence
Original CVE published
2026-08-04
Original CVE updated
2026-09-09
Advisory published
2026-08-04
Advisory updated
2026-09-09

Who should care

Defenders of applications using @langchain/langgraph-checkpoint-mongodb versions 1.3.0 and below, especially in multi-tenant or user-isolated setups, should assess exposure and prioritize verification and remediation.

Why it matters

CVE-2026-48121 is a NoSQL injection vulnerability in @langchain/langgraph-checkpoint-mongodb versions 1.3.0 and below. Defenders should prioritize verification and remediation to prevent potential leakage of checkpoints and bypassing of thread scoping.

  • Potential leakage of checkpoints, including pending writes, across tenants
  • Bypassing thread scoping due to NoSQL injection
  • Verification of input validation and schema enforcement in config.configurable

Technical summary

The @langchain/langgraph-checkpoint-mongodb package versions 1.3.0 and below are vulnerable to NoSQL injection due to lack of type enforcement on checkpoint identifiers passed into MongoDB find() queries. This could lead to potential leakage of checkpoints and bypassing of thread scoping. The issue has been fixed in version 1.3.1. Defenders should prioritize verifying and upgrading to version 1.3.1 or later, and validating input to config.configurable. 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.

Defensive priority

Defenders should prioritize verifying and upgrading to version 1.3.1 or later, and validating input to config.configurable.

Recommended defensive actions

  • Verify and upgrade to version 1.3.1 or later
  • Validate input to config.configurable
  • Review and update multi-tenant or user-isolated setups
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented

Evidence notes

The CVE record and NVD entry provide details on the NoSQL injection vulnerability in @langchain/langgraph-checkpoint-mongodb versions 1.3.0 and below. The vulnerability allows for potential leakage of checkpoints and bypassing of thread scoping due to lack of type enforcement on checkpoint identifiers. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema. The issue has been fixed in version 1.3.1.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-48121 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-48121

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-48121 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-48121

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.