CVSS 3.1
9.1 criticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:NCritical (9.1) in langchain langgraph-sdk. EPSS 0.2% estimated probability of exploitation activity in the next 30 days. Fixed in langgraph-sdk 0.3.15.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:Nlanggraph-sdk (PyPI): fixed in 0.3.15langgraph (PyPI): fixed in 0.3.15Explain CVE-2026-48776 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-48776?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-48776?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-2026-48776 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.
From the NVD's CPE matches.
| Product | Affected |
|---|---|
| langchain:langgraph-sdk | before 0.3.15 |
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-w39p-vh2g-g8g5 | PyPI | langgraph-sdk | <0.3.15 | 0.3.15 |
| PYSEC-2026-2194 | PyPI | langgraph | <0.3.15 | 0.3.15 |
| PYSEC-2026-2575 | PyPI | langgraph-sdk | <0.3.15 | 0.3.15 |
Red Hat rates this Moderate.
A flaw was found in the LangGraph Python SDK. Unsafe URL path construction allows unauthorized resource access when untrusted end-user input is passed directly into SDK identifier parameters. An attacker can craft identifier values containing path traversal sequences to access resources outside the intended scope.
Validate all identifier values (e.g., by parsing as UUIDs and rejecting non-conforming input) at the application boundary before passing them to langgraph-sdk methods. Avoid forwarding untrusted end-user input directly into SDK identifier parameters. For deployments using URL-prefix-based authorization upstream of LangGraph servers, enforce authorization at the LangGraph server layer or on parsed-and-validated request paths rather than on raw URL prefixes. Updating langgraph-sdk to version 0.3.15 or later applies percent-encoding to path segments and fully resolves this issue.
| Product | Package | State | Advisory |
|---|---|---|---|
| Exploit Intelligence | exploit-intelligence-tech-preview/vulnerability-analysis-rhel9 | Fix deferred | |
| Migration Toolkit for Applications 8 | mta/mta-solution-server-rhel9 | Fix deferred | |
| OpenShift Lightspeed | openshift-lightspeed/lightspeed-service-api-rhel9 | Fix deferred | |
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-25/lightspeed-rhel8 | Fix deferred | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-autorag-rhel9 | Fix deferred | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9 | Fix deferred | |
| Red Hat OpenShift AI (RHOAI) | rhoai/odh-trustyai-nemo-guardrails-server-rhel9 | Fix 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-2026-48776.
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.