cve.bz

CVE-2026-104873 langchain-ai langgraph: Incorrect Authorization

7.6 highEPSS 0.3%Fix available

High (7.6) in langchain-ai langgraph. EPSS 0.3% estimated probability of exploitation activity in the next 30 days. Fixed in langgraph-sdk 0.4.4.

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 0.1.45 until 0.4.4, the langgraph-sdk resource-scoped authorization decorators @auth.on.threads, @auth.on.assistants, and @auth.on.crons ignore the actions argument and register the selected handler for every action on the resource. Because that wildcard resource handler is selected before broader fallback handlers, an authenticated user may bypass fallback action, ownership, or permission checks and read, update, or delete another user's resource. Only Python deployments using actions on the affected decorators are vulnerable, and a deployment remains protected when the selected handler independently enforces all required checks for every action it receives. This issue is fixed in version 0.4.4.

Severity

CVSS 4.0

7.6 high
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N
EPSS
0.3% (unchanged from 0.3% a week ago; 0.3% 30 days ago) estimated probability of exploitation activity in the next 30 days; 17th 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 2026-10-05. 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-863 Incorrect Authorization
OWASP Top 10
A01:2025 Broken Access Control
Published
Modified
NVD analysis
Awaiting analysis
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-104873 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-104873?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-104873?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-2026-104873 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>= 0.1.45, < 0.4.4

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-fvww-7h3r-vfhpPyPIlanggraph-sdk>=0.1.45 <0.4.40.4.4
PYSEC-2026-4240PyPIlanggraph-sdk>=0.1.45 <0.4.40.4.4

Linux distributions

DistributionReleasePackageFixed inAdvisory
openSUSETumbleweedpython-langgraph-sdk0.4.9-1.1openSUSE-SU-2026:12279-1

From the distributions' data via OSV.dev: SUSE security data, CC BY 4.0. Modified: reformatted and linked to CVE records. Credits. On the distributions' own pages: openSUSE.

Red Hat

Red Hat rates this Important.

Red Hat's statement

This flaw is rated as having Important impact because authenticated remote users could bypass intended authorization boundaries in multi-tenant environments, resulting in unauthorized access or modification of sensitive resources. In Red Hat products integrating this SDK, exposure is limited to environments where custom authentication policies filter specific resource operations. Furthermore, the issue only presents a risk if the custom handler does not enforce permissions across all attempted operations independently.

Red Hat's mitigation

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

ProductPackageStateAdvisory
Red Hat OpenShift AI 3.4rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9:1791785804Fixed 2026-10-19RHSA-2026:84734
Red Hat OpenShift AI 3.4rhoai/odh-trustyai-nemo-guardrails-server-rhel9:1791556128Fixed 2026-10-19RHSA-2026:84734
Red Hat OpenShift AI 3.5rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9:1791953275Fixed 2026-10-21RHSA-2026:86891
Ansible Automation Orchestrator 2026ansible-automation-platform/automation-orchestrator-backend-rhel9Affected
Exploit Intelligenceexploit-intelligence/vulnerability-analysis-rhel9Affected
Migration Toolkit for Applications 8mta/mta-solution-server-rhel9Affected
OpenShift Lightspeedopenshift-lightspeed/lightspeed-agentic-sandbox-rhel9Affected
OpenShift Lightspeedopenshift-lightspeed/lightspeed-service-api-rhel9Affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/lightspeed-rhel8Not affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-gaudi-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-rocm-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/disk-image-cuda-rhel9Affected

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-2026-104873.

References

Check your stackJSON