LangGraph SDK has unsafe URL path construction_CVE-2026-48776

4.2 / 10

MEDIUM

CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:N

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.

Basic Information

ID CVE-2026-48776

Source GitHub_M

Published Jun 16, 2026 at 19:51

Affected Product

Vendor langchain-ai

Product langchain-ai

Version < 1.2.1

Affected Versions langchain-ai langchain-ai < 1.2.1
langchain-ai langchain-sdk < 0.3.15

CWE Classification

CWE-22 CWE-863

References

{
    "lastseen": "",
    "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.",
    "published": "2026-06-16T19:51:09.464Z",
    "modified": "2026-06-16T19:51:09.464Z",
    "type": "cve",
    "title": "LangGraph SDK has unsafe URL path construction",
    "source": "GitHub_M",
    "references": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-w39p-vh2g-g8g5\nhttps://github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.3.15",
    "id": "CVE-2026-48776",
    "bulletinFamily": "",
    "cwe": [
        "CWE-22",
        "CWE-863"
    ],
    "cvelist": null,
    "sourceData": "langchain-ai langchain-ai < 1.2.1\nlangchain-ai langchain-sdk < 0.3.15",
    "sourceHref": "",
    "cvss": {
        "score": 4.2,
        "severity": "MEDIUM",
        "vector": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:N",
        "version": "3.1"
    },
    "cvss2": [],
    "cvss3": {
        "version": "",
        "vectorString": "",
        "baseScore": 0,
        "baseSeverity": "",
        "attackVector": "",
        "attackComplexity": "",
        "privilegesRequired": "",
        "userInteraction": "",
        "scope": "",
        "confidentialityImpact": "",
        "integrityImpact": "",
        "availabilityImpact": "",
        "cvssV3": {
            "version": "",
            "vectorString": "",
            "baseScore": 0,
            "baseSeverity": "",
            "attackVector": "",
            "attackComplexity": "",
            "privilegesRequired": "",
            "userInteraction": "",
            "scope": "",
            "confidentialityImpact": "",
            "integrityImpact": "",
            "availabilityImpact": ""
        }
    },
    "href": "",
    "category_name": "CVE",
    "post_link": "",
    "product": "langchain-ai",
    "version": "< 1.2.1",
    "vendor": "langchain-ai",
    "ai_description": "",
    "ai_severity": "",
    "ai_vendor": "",
    "ai_product": "",
    "ai_version": "",
    "ai_score": 0
}