CVE-2026-48776
Received Received - Intake
Path Traversal in LangGraph Python SDK

Publication date: 2026-06-17

Last updated on: 2026-06-17

Assigner: GitHub, Inc.

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 Scores
EPSS Scores
Probability:
Percentile:
Meta Information
Published
2026-06-17
Last Modified
2026-06-17
Generated
2026-06-17
AI Q&A
2026-06-17
EPSS Evaluated
N/A
NVD
Affected Vendors & Products
Showing 2 associated CPEs
Vendor Product Version / Range
langchain-ai langgraph_sdk to 0.3.15 (exc)
langchain-ai langgraph_sdk 0.3.15
Helpful Resources
Exploitability
CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-863 The 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.
CWE-22 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.
Attack-Flow Graph
AI Quick Actions
Instant insights powered by AI
Executive Summary

The vulnerability in LangGraph Python SDK versions 0.3.14 and earlier involves unsafe URL path construction. The SDK directly inserts caller-supplied identifier values into HTTP request paths without properly sanitizing them. If these identifiers contain special URL characters, the resulting request can target a different resource or resource type than intended.

This issue is especially risky when the SDK receives identifiers from untrusted sources, such as end-user input, without validating them against expected formats like UUIDs. In such cases, attackers could cause unintended access, modification, or deletion of resources beyond their authorization scope.

The vulnerability is most critical in deployments relying on URL-prefix-based authorization at upstream layers (e.g., reverse proxies or gateways), where authorization decisions are made based on the intended SDK call path rather than the actual final request path.

This issue has been fixed in version 0.3.15 by introducing path-segment encoding for identifiers, ensuring special characters are properly escaped.

Impact Analysis

This vulnerability can lead to unintended access, modification, or deletion of resources beyond the calling user's authorization scope if untrusted identifier values are passed to the SDK without validation.

Attackers could exploit special characters in identifiers to manipulate URL paths, potentially bypassing authorization controls that rely on URL prefixes.

The impact includes breaches of confidentiality and integrity of resources managed through the LangGraph SDK.

However, exploitation requires specific conditions such as receiving untrusted input and relying solely on URL-prefix-based authorization, and the vulnerability has a moderate CVSS score of 4.2.

Detection Guidance

This vulnerability involves unsafe URL path construction in LangGraph Python SDK versions 0.3.14 and earlier, where caller-supplied identifiers are not sanitized and may contain special URL characters leading to unintended resource access.

To detect this vulnerability on your system, you should check the version of the langgraph-sdk installed and used in your environment.

  • Run a command to check the installed version of langgraph-sdk, for example: pip show langgraph-sdk
  • Inspect your application code or logs for usage of the LangGraph SDK with identifier values that come from untrusted sources without validation.
  • Monitor HTTP request paths generated by the SDK for unexpected or malformed URL paths that include special characters in identifiers.

There are no specific detection commands provided in the resources, but focusing on version checks and code review for unsanitized identifier usage is recommended.

Mitigation Strategies

The primary mitigation step is to upgrade the LangGraph Python SDK to version 0.3.15 or later, where the vulnerability has been fixed by introducing proper percent-encoding of caller-supplied identifiers in URL paths.

Additionally, validate all identifier values passed to the SDK, ensuring they conform to expected safe formats such as UUIDs before use.

Avoid relying solely on URL-prefix-based authorization at upstream layers like reverse proxies or gateways, since the final request path may differ from the intended path due to this vulnerability.

Review and update any security controls or authorization mechanisms to ensure they validate the actual request paths after SDK processing.

Compliance Impact

The vulnerability in LangGraph SDK versions 0.3.14 and earlier involves unsafe URL path construction that can lead to unintended access, modification, or deletion of resources beyond the calling user's authorization scope. This could result in confidentiality and integrity breaches of data.

In environments where the SDK receives identifier values from untrusted sources without proper validation, and where authorization relies on URL-prefix-based checks, this vulnerability could allow unauthorized access to sensitive information.

Such unauthorized access or modification of data could potentially violate compliance requirements of standards and regulations like GDPR or HIPAA, which mandate strict controls over data confidentiality, integrity, and access authorization.

Therefore, organizations using affected versions of the SDK should upgrade to version 0.3.15 and implement proper validation of identifiers to maintain compliance with these regulations.

Chat Assistant
Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-48776. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70
EPSS Chart