cve.bz

CVE-2026-118667 langchain-ai: Path traversal

4.3 mediumEPSS 0.4%Fix available

Medium (4.3) in langchain-ai. EPSS 0.4% estimated probability of exploitation activity in the next 30 days. Fixed in langgraph-sdk 0.4.6.

On this page
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.

Severity

CVSS 3.1

4.3 medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
EPSS
0.4% (unchanged from 0.4% a week ago) estimated probability of exploitation activity in the next 30 days; 34th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: no · Technical impact: partial, assessed 2026-10-29. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-22 Improper Limitation of a Pathname to a Restricted Directory (Path traversal)
OWASP Top 10
A01:2025 Broken Access Control
Published
Modified
NVD analysis
Awaiting analysis
Record from
the NVD, synced

Fix and patched versions

  • langgraph-sdk (PyPI): fixed in 0.4.6
  • langgraph (PyPI): fixed in 1.2.14

Ask an AI about this CVE

Show the promptExplain CVE-2026-118667 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-118667?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-118667?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-118667 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
langchain-ai langgraph>= 1.2.3, < 1.2.14
langchain-ai langgraph-sdk>= 0.4.0, < 0.4.6

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-3fx2-cqw9-xr3cPyPIlanggraph-sdk>=0.4.0 <0.4.60.4.6
GHSA-3fx2-cqw9-xr3cPyPIlanggraph>=1.2.3 <1.2.141.2.14

Red Hat

Red Hat rates this Moderate.

Red Hat's statement

Red Hat has evaluated this vulnerability as having a Moderate severity because exploitation requires an application to accept unvalidated user input into streaming thread or assistant parameters, and the flaw only permits read-only requests without granting arbitrary modification capabilities. In affected Red Hat environments utilizing LangGraph client integrations, exposure depends on whether external users can influence streaming workflow arguments. Furthermore, potential data exposure is restricted to accessible paths on the authenticated API server.

ProductPackageStateAdvisory
Ansible Automation Orchestrator 2026ansible-automation-platform/automation-orchestrator-backend-rhel9Fix deferred
Exploit Intelligenceexploit-intelligence/vulnerability-analysis-rhel9Out of support scope
Migration Toolkit for Applications 8mta/mta-solution-server-rhel9Fix deferred
OpenShift Lightspeedopenshift-lightspeed/lightspeed-agentic-sandbox-rhel9Fix deferred
OpenShift Lightspeedopenshift-lightspeed/lightspeed-service-api-rhel9Fix deferred
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/lightspeed-rhel8Out of support scope
Red Hat OpenShift AI (RHOAI)rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-trustyai-nemo-guardrails-server-rhel9Fix deferred

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-118667.

Attack patterns (CAPEC)

  • CAPEC-64 Using Slashes and URL Encoding Combined to Bypass Validation Logic Likelihood: High · Severity: High
  • CAPEC-76 Manipulating Web Input to File System Calls Likelihood: High · Severity: Very High
  • CAPEC-78 Using Escaped Slashes in Alternate Encoding Likelihood: High · Severity: High
  • CAPEC-79 Using Slashes in Alternate Encoding Likelihood: High · Severity: High
  • CAPEC-126 Path Traversal Likelihood: High · Severity: Very High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON