# CVE-2026-71433: LangGraph incorrect authorization in Postgres and SQLite namespace matching

Source: https://junglewise.ai/threats/cve-2026-71433-langgraph-incorrect-authorization-in-postgres-and-sqlite  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-08-06. Updated: 2026-08-06  
License: CC BY 4.0 with a link back

CVE-2026-71433 · Severity: medium · CVSS 5.3 · Published 2026-08-06

LangGraph is a library used to build stateful AI agents. A flaw in how it handles data storage in Postgres and SQLite databases could allow one user or tenant to see data belonging to another if their identifiers share similar names (e.g., 'user1' seeing data for 'user12'). This could lead to unauthorized access to sensitive conversation history or agent memory in multi-tenant applications.

Technologies: [langgraph-checkpoint-sqlite (PyPI)](https://junglewise.ai/threats/technologies/langgraph-checkpoint-sqlite). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-71433 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-71433 being exploited in the wild.

**How severe is CVE-2026-71433?** Medium severity, with a CVSS score of 5.3, published 6 August 2026.

**Which products and versions are affected?** langgraph-checkpoint-postgres (PyPI) < 3.1.1, ECOSYSTEM:introduced=0,fixed=3.1.1; langgraph-checkpoint-sqlite (PyPI) < 3.1.1, ECOSYSTEM:introduced=0,fixed=3.1.1.

**Is there a fix for CVE-2026-71433?** Yes. langgraph-checkpoint-postgres (PyPI): upgrade to 3.1.1 or later; langgraph-checkpoint-sqlite (PyPI): upgrade to 3.1.1 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-71433 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-71433?** Check whether you run langgraph-checkpoint-postgres (PyPI) or langgraph-checkpoint-sqlite (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- langgraph-checkpoint-postgres (PyPI): upgrade to 3.1.1 or later

  ```sh
  pip install "langgraph-checkpoint-postgres>=3.1.1"
  ```

- langgraph-checkpoint-sqlite (PyPI): upgrade to 3.1.1 or later

  ```sh
  pip install "langgraph-checkpoint-sqlite>=3.1.1"
  ```


## Technical details

The Postgres and SQLite store implementations in LangGraph persist hierarchical namespaces as dot-joined strings (e.g., 'memories.alice'). Scoped read operations like 'search' and 'list_namespaces' used SQL 'LIKE' patterns (e.g., 'path%') for matching. Because 'LIKE' does not recognize the dot separator, a query for 'foo' would incorrectly match 'foobar' or 'foo2'. Additionally, the implementation failed to escape SQL metacharacters like '_' and '%', allowing them to act as wildcards. This results in an authorization bypass where a user scoped to one namespace can retrieve items from another. The issue is fixed in version 3.1.1 by implementing segment-aware matching and proper character escaping.

## Affected products

- LangChain AI langgraph-checkpoint-postgres < 3.1.1
- LangChain AI langgraph-checkpoint-sqlite < 3.1.1

## Identifiers

- CVE-2026-71433
- GHSA-47pj-3jcm-6whg
- PYSEC-2026-3635
- PYSEC-2026-3636

## Timeline

- 2026-07-30: patched: Fix merged into main branch
- 2026-08-06: advisory: GitHub Advisory published

## References

- [https://github.com/langchain-ai/langgraph/security/advisories/GHSA-47pj-3jcm-6whg](https://github.com/langchain-ai/langgraph/security/advisories/GHSA-47pj-3jcm-6whg)
- [https://github.com/langchain-ai/langgraph/pull/8478](https://github.com/langchain-ai/langgraph/pull/8478)
- [https://github.com/langchain-ai/langgraph/commit/66ebe1a0da921e73f0f9f879ba105d314c079f7c](https://github.com/langchain-ai/langgraph/commit/66ebe1a0da921e73f0f9f879ba105d314c079f7c)
- [https://github.com/langchain-ai/langgraph/releases/tag/checkpointpostgres%3D%3D3.1.1](https://github.com/langchain-ai/langgraph/releases/tag/checkpointpostgres%3D%3D3.1.1)
- [https://github.com/langchain-ai/langgraph/releases/tag/checkpointsqlite%3D%3D3.1.1](https://github.com/langchain-ai/langgraph/releases/tag/checkpointsqlite%3D%3D3.1.1)
- [https://api.github.com/repos/langchain-ai/langgraph/security-advisories/GHSA-47pj-3jcm-6whg](https://api.github.com/repos/langchain-ai/langgraph/security-advisories/GHSA-47pj-3jcm-6whg)

## Related threats

- [LangGraph checkpoint savers namespace validation bypass in SQLite and Postgres](https://junglewise.ai/threats/cve-2026-115883-langgraph-checkpoint-savers-provide-postgres-and-sqlite-backed)
- [PYSEC-2026-1530 - LangGraph's SQLite is vulnerable to SQL injection via metadata filter key in SQLite checkpointer list method](https://junglewise.ai/threats/cve-2025-67644-langgraph-s-sqlite-is-vulnerable-to-sql-injection-via-metadata)
- [LangGraph SQLite Checkpoint Filter Key SQL Injection POC for SqliteStore](https://junglewise.ai/threats/cve-2025-64104-langgraph-sqlite-checkpoint-filter-key-sql-injection-poc-for)
- [A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation.](https://junglewise.ai/threats/cve-2025-8709-langgraph-s-sqlite-store-implementation-has-a-sql-injection)