PatchSiren cyber security CVE debrief
CVE-2026-48776 langchain-ai CVE debrief
The LangGraph Python SDK, used to connect to LangGraph API servers and manage assistants, threads, and stream runs, has a vulnerability in versions 0.3.14 and prior. The issue arises from unsafe URL path construction through unsanitized caller-supplied identifier values used in HTTP request paths for resource operations. This could lead to unintended access, modification, or deletion of resources beyond the calling user's authorization scope, particularly in deployments where end-user-supplied values are directly forwarded into SDK identifier parameters without validation. The vulnerability has been fixed in version 0.3.15.
- Vendor
- langchain-ai
- Product
- Unknown
- CVSS
- MEDIUM 4.2
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-06-17
- Original CVE updated
- 2026-06-26
- Advisory published
- 2026-06-17
- Advisory updated
- 2026-06-26
Who should care
Organizations using LangGraph Python SDK versions 0.3.14 and prior, especially those that forward end-user-supplied values directly into SDK identifier parameters without validation, should be aware of this vulnerability. This issue is particularly relevant for deployments relying on URL-prefix-based authorization at an upstream layer.
Technical summary
The LangGraph Python SDK constructs HTTP request paths using caller-supplied identifier values without proper sanitization. This allows identifiers with special URL path characters to potentially redirect requests to different resources than intended. The vulnerability is exacerbated in scenarios where the SDK receives identifier values from untrusted sources and where authorization decisions are made based on the SDK call's intended path rather than the final delivered request path. The issue is addressed in version 0.3.15 of the SDK.
Defensive priority
MEDIUM
Recommended defensive actions
- Update LangGraph Python SDK to version 0.3.15 or later
- Validate identifier values against an expected format (such as a UUID) before passing them to the SDK
- Implement additional authorization checks at the application level to ensure access control
- Review and update URL-prefix-based authorization configurations at upstream layers
- Monitor for and restrict suspicious traffic patterns that could exploit this vulnerability
- Consider using a Web Application Firewall (WAF) to detect and prevent attacks
Evidence notes
The information provided is based on the CVE record and details from the LangGraph Python SDK security advisory. The vulnerability's impact and recommended actions are derived from the CVSS score and vector, as well as the nature of the vulnerability itself.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-48776 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-48776
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-48776 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-48776
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
Source reference
Unverified legacy reference
URL: https://github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.3.15
-
Source reference
Unverified legacy reference
URL: https://github.com/langchain-ai/langgraph/security/advisories/GHSA-w39p-vh2g-g8g5
Methodology and review provenance
AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.