Skip to main content
EPSS 0.2%top 87%

CVE-2026-71433: CWE-200: Exposure of Sensitive Information to an Unauthorized Actor in langchain-ai langgraph

0
Medium
Published: 08/06/2026 (08/06/2026, 19:03:09 UTC)
Source: CVE Database V5
Vendor/Project: langchain-ai
Product: langgraph

Description

A vulnerability in langgraph's checkpoint saver implementations for Postgres and SQLite allows an authenticated user to access stored items belonging to other tenants or users due to improper namespace scoping. This occurs because hierarchical namespaces are persisted as dot-joined strings and reads are scoped by prefix matching, which can overlap with sibling namespaces or those containing unescaped pattern metacharacters. The issue affects versions prior to 3.1.1 and is fixed in version 3.1.1.

CVSS v3.1

Score 5.3medium

Attack Vector
Network
Attack Complexity
High
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
None
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:N/A:N

Affected software

langchain-ai

langgraph

Affected versions
<3.1.1

langchain-ai

langgraph-checkpoint-sqlite

Affected versions
<3.1.1

langchain-ai

langgraph-checkpoint-postgres

Affected versions
<3.1.1
GitHub Actionsmore threats →ai
langchain-ai/langgraph-checkpoint-postgres
pkg:github/langchain-ai/langgraph-checkpoint-postgres
Affected versions
<3.1.1
GitHub Actionsmore threats →ai
langchain-ai/langgraph-checkpoint-sqlite
pkg:github/langchain-ai/langgraph-checkpoint-sqlite
Affected versions
<3.1.1

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 08/14/2026, 16:17:09 UTC

Technical Analysis

LangGraph Checkpoint Postgres and SQLite implementations persist hierarchical namespaces as dot-joined strings and scope reads by prefix matching. Prior to version 3.1.1, this method allowed an authenticated caller to retrieve stored items from other tenants or users because a read scoped to one namespace could also match sibling namespaces sharing the same leading characters or namespaces with unescaped pattern metacharacters. No crafted input is required to exploit this issue. The vulnerability is addressed in langgraph-checkpoint-postgres and langgraph-checkpoint-sqlite version 3.1.1.

Potential Impact

An authenticated user can access sensitive information stored under other tenants' or users' namespaces without authorization. This exposure of sensitive data violates confidentiality but does not affect integrity or availability.

Mitigation Recommendations

Upgrade langgraph-checkpoint-postgres and langgraph-checkpoint-sqlite to version 3.1.1 or later, where the issue is fixed. Patch status is confirmed by the vendor advisory indicating the fix in version 3.1.1.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-08-06T16:28:51.182Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6a75070dbf8831d5395f5c83

Added to database: 08/06/2026, 22:13:33 UTC

Last enriched: 08/14/2026, 16:17:09 UTC

Last updated: 09/21/2026, 22:01:37 UTC

Views: 42

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses