PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-71433 langchain-ai CVE debrief

CVE-2026-71433 LangGraph Checkpoint vulnerability allows unauthorized data access. LangGraph Checkpoint Postgres and SQLite implementations prior to version 3.1.1 improperly handled namespace scoping, permitting authenticated callers to retrieve data from other tenants or users via scoped searches or namespace listing. The vulnerability impacts data confidentiality and requires verification of patched versions and restricted access to sensitive data. This issue is fixed in versions 3.1.1 of langgraph-checkpoint-postgres and langgraph-checkpoint-sqlite.

Vendor
langchain-ai
Product
langgraph
CVSS
MEDIUM 5.3
CISA KEV
Not listed in stored evidence
Original CVE published
2026-08-06
Original CVE updated
2026-09-10
Advisory published
2026-08-06
Advisory updated
2026-09-10

Who should care

LangGraph Checkpoint users, administrators, and security teams should assess exposure and verify patched versions. They should also restrict access to sensitive data and monitor for unusual activity. Security teams need to review compensating controls for exposed systems and track exceptions.

Why it matters

CVE-2026-71433 LangGraph Checkpoint vulnerability allows unauthorized data access; users should verify version 3.1.1 or later is deployed and restrict access to sensitive data.

  • Potential unauthorized data access for authenticated users
  • Need to verify and update LangGraph Checkpoint versions
  • Possible impact on data confidentiality
  • Requires review of namespace scoping and access controls

Technical summary

LangGraph Checkpoint Postgres and SQLite implementations prior to 3.1.1 used a flawed namespace scoping mechanism, allowing authenticated callers to access data from other tenants or users. This issue is fixed in versions 3.1.1 of langgraph-checkpoint-postgres and langgraph-checkpoint-sqlite. The vulnerability impacts data confidentiality and requires verification of patched versions and restricted access to sensitive data. The flaw permits authenticated callers to retrieve stored items belonging to another tenant or user through an ordinary scoped search or list namespaces call.

Defensive priority

Medium priority for LangGraph Checkpoint users; verify version 3.1.1 or later is deployed.

Recommended defensive actions

  • Verify LangGraph Checkpoint Postgres and SQLite versions are 3.1.1 or later
  • Restrict access to sensitive namespaces and data
  • Monitor for unusual scoped search or namespace listing activity
  • 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
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

Official CVE and NVD records provide details on the vulnerability. Vendor GitHub repository contains advisories and patches for LangGraph Checkpoint Postgres and SQLite implementations. The CVE record was published on 2026-08-06T22:18:30.107Z and has not been modified since then. The vulnerability allows unauthorized data access, impacting data confidentiality. LangGraph Checkpoint users should verify version 3.1.1 or later is deployed and restrict access to sensitive data.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-71433 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-71433

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

  • CVE-2026-71433 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-71433

    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.