Skip to content
Fencer Intel
medium 5.3

CVE-2026-71433 json

LangGraph: Namespace prefix matching crosses segment boundaries in Postgres and SQLite stores

published 3mo ago modified 2mo ago also EUVD-2026-54227 , GHSA-47pj-3jcm-6whg , PYSEC-2026-3635 , PYSEC-2026-3636

cvss
5.3
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 30%
public exploits
0
none known

Summary

LangGraph Checkpoint Postgres and SQLite Checkpoint are the Postgres and SQLite implementations of LangGraph's checkpoint saver. Prior to 3.1.1, the langgraph-checkpoint-postgres and langgraph-checkpoint-sqlite packages persisted hierarchical namespaces as a dot joined string and scoped reads by matching that string as a simple prefix pattern, so a read scoped to one namespace could also match a sibling namespace whose flattened form shares the same leading characters, or a namespace label containing unescaped pattern metacharacters, allowing an authenticated caller to retrieve stored items belonging to another tenant or user through an ordinary scoped search or list namespaces call, with no crafted input required. This issue is fixed in versions 3.1.1 of langgraph-checkpoint-postgres and langgraph-checkpoint-sqlite.

Patch / fix

  • pypi langgraph-checkpoint-postgres 3.1.1
  • pypi langgraph-checkpoint-sqlite 3.1.1
  • langchain-ai langgraph-checkpoint-postgres 3.1.1
  • langchain langgraph-checkpoint-postgres 3.1.1
  • langchain-ai langgraph-checkpoint-sqlite 3.1.1
  • langchain langgraph-checkpoint-sqlite 3.1.1

Is CVE-2026-71433 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
3mo ago

Exploit prediction

0.36% chance of exploitation in the next 30 days, higher than 30% of all scored CVEs (FIRST EPSS, 2026-11-11).

CVSS scores

assigned by version score vector
CNA 3.1 5.3 CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:N/A:N
GitHub 3.1 5.3 CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:N/A:N
OSV 3.1 5.3 CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi langgraph-checkpoint-postgres
<3.1.1
3.1.1
pypi langgraph-checkpoint-sqlite
<3.1.1
3.1.1

Affected products

  • langchain-ai langgraph
  • langchain-ai langgraph-checkpoint-sqlite
  • langchain-ai langgraph-checkpoint-postgres

Classification

Weakness
  • CWE-200 Exposure of Sensitive Information to an Unauthorized Actor
  • CWE-863 Incorrect Authorization

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

The maintainers of langchain-ai/langgraph published their own advisory on GitHub. Reviewed sources take precedence over it.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.