LangGraph SDK has unsafe URL path construction
Summary
| CVE | CVE-2026-48776 |
|---|---|
| State | PUBLISHED |
| Assigner | GitHub_M |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2026-06-17 10:55:15 UTC |
| Updated | 2026-06-17 16:30:36 UTC |
| Description | LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. Versions 0.3.14 and prior have unsafe URL path construction through unsanitized caller-supplied identifier values used in HTTP request paths for resource operations. Without sanitization of those values, identifiers that contain characters with special meaning in URL paths could cause the resulting request to address a different resource (and potentially a different resource type) than the SDK method's call site indicates. In deployments where the SDK receives identifier values that originate from untrusted sources, this could result in unintended access, modification, or deletion of resources beyond the calling user's authorization scope. This issue is most consequential in deployments that forward end-user-supplied values directly into SDK identifier parameters without first validating them against an expected format (such as a UUID), and rely on URL-prefix-based authorization at an upstream layer (reverse proxy, edge gateway, WAF), where the authorization decision is made on the SDK call's intended path rather than on the final delivered request path. The issue has been fixed in version 0.3.15. |
Risk And Classification
Primary CVSS: v3.1 4.2 MEDIUM from [email protected]
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:N
EPSS: 0.002200000 probability, percentile 0.123140000 (date 2026-06-17)
Problem Types: CWE-22 | CWE-863 | CWE-22 CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') | CWE-863 CWE-863: Incorrect Authorization
| Version | Source | Type | Score | Severity | Vector |
|---|---|---|---|---|---|
| 3.1 | [email protected] | Secondary | 4.2 | MEDIUM | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:N |
| 3.1 | CNA | DECLARED | 4.2 | MEDIUM | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:N |
CVSS v3.1 Breakdown
Attack Vector
NetworkAttack Complexity
HighPrivileges Required
LowUser Interaction
NoneScope
UnchangedConfidentiality
LowIntegrity
LowAvailability
NoneCVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:N
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|---|---|---|---|
| CNA | Langchain-ai | Langchain-ai | affected < 1.2.1 | Not specified |
| CNA | Langchain-ai | Langchain-sdk | affected < 0.3.15 | Not specified |
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.3.15 | [email protected] | github.com | |
| github.com/langchain-ai/langgraph/security/advisories/GHSA-w39p-vh2g-g8g5 | [email protected] | github.com | |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.