Skip to content
Fencer Vulns
medium 4.3

CVE-2026-118667 json

LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requests

published 2026-10-28 11 d ago modified 2026-10-29 10 d ago also GHSA-3fx2-cqw9-xr3c , EUVD-2026-112474

cvss
4.3
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 33%
public exploits
0
none known

Summary

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From langgraph-sdk 0.4.0 until 0.4.6, and from langgraph 1.2.3 until 1.2.14 when RemoteGraph v3 streaming uses an affected langgraph-sdk version, the synchronous and asynchronous v3 stream get_tree and _fetch_state helpers interpolate caller-controlled assistant_id and thread_id values into authenticated GET request paths without using _quote_path_param. Relative path segments can therefore be normalized into another readable path on the configured server while retaining authentication headers. This issue is fixed in langgraph-sdk 0.4.6 and langgraph 1.2.14.

Patch / fix

  • pypi langgraph-sdk 0.4.6
  • pypi langgraph 1.2.14

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-118667 updated cvss 4.3

langgraph-sdk: langgraph: LangGraph: Information disclosure via path traversal in streaming helpers

  • Red Hat Ansible Automation Orchestrator 2026 ansible-automation-platform/automation-orchestrator-backend-rhel9
    affected: no fix available “Fix deferred”
  • Red Hat Exploit Intelligence exploit-intelligence/vulnerability-analysis-rhel9
    affected: no fix planned “Out of support scope”
  • Red Hat Migration Toolkit for Applications 8 mta/mta-solution-server-rhel9 Red Hat OpenShift Lightspeed openshift-lightspeed/lightspeed-service-api-rhel9, openshift-lightspeed/lightspeed-agentic-sandbox-rhel9
    affected: no fix available “Fix deferred”
  • Red Hat Ansible Automation Platform 2 ansible-automation-platform-25/lightspeed-rhel8
    affected: no fix planned “Out of support scope”
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9, rhoai/odh-trustyai-nemo-guardrails-server-rhel9
    affected: no fix available “Fix deferred”

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
10 d ago

Exploit prediction

0.39% chance of exploitation in the next 30 days, higher than 33% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 4.3 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
GitHub 3.1 4.3 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi langgraph-sdk
>=0.4.0, <0.4.6
0.4.6
pypi langgraph
>=1.2.3, <1.2.14
1.2.14

Affected products

  • langchain-ai langgraph
  • langchain-ai langgraph-sdk

Classification

Weakness
  • CWE-22 Improper Limitation of a Pathname to a Restricted Directory

References

Sources

Fencer Vulns 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.