CVE-2026-48776: langchain-ai Path Traversal
Vulnerability summary
CVE-2026-48776 is a critical (CVSS 9.1) Path Traversal vulnerability in langchain-ai. EPSS estimates a 0.29% chance of exploitation in the next 30 days, higher than 20.5% of scored vulnerabilities.
Timeline
- 16-06-2026PublishedVulnerability first disclosed.
- 17-06-2026Last modifiedVulnerability information updated.
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.
CVSS metrics
3 scores · 3 sources · 1 version- CVE.orgCNA4.2MediumCVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:NDiffers
- OSV · PypiEcosystem advisory · calculated4.2MediumCVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:NDiffers
EPSS trend
Probability
0.29%
Chance of exploitation in the next 30 days
Percentile
21%
Versus all other CVEs
30-day change
+0.08 pp
From 0.22% on 19-09-2026
Known exploited
Compare KEV catalogsNot in any of the 3 tracked catalogs.
Public exploits
0 foundNo public exploits indexed.
Weaknesses
CWE · root cause- CWE-22Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')The product uses external input to construct a pathname that is intended to identify a file or directory that is located underneath a restricted parent directory, but the product does not properly neutralize special elements within the pathname that can cause the pathname to resolve to a location that is outside of the restricted directory.
- CWE-863Incorrect AuthorizationThe product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.
Affected systems
Langchain-ai2 products
- langchain-ai< 1.2.1
- langchain-sdk< 0.3.15
PyPI2 products
- langgraph< 0.3.15
- langgraph-sdk< 0.3.15
Langchain1 product
- langgraph-sdk< 0.3.15
3 vendors · 5 products
References
8 links- github.com/langchain-ai/langgraph/security/advisories/GHSA-w39p-vh2g-g8g5X Refsource CONFIRMWEBAdvisoryVendor Advisory
- github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.3.15X Refsource MISCWEBAdvisoryRelease Notes