Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-55235— langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication

Quick assessment

Affected
langchain-ai langgraph-api
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

langgraph-api 实现了 LangGraph API，用于快速开发和测试。在 0.10.0 之前的版本中，langgraph-api 允许某个运行（run）或定时任务（cron）指定一个相对路径的 Webhook 目标，并通过进程内回环传输（in-process loopback transport）进行交付。认证中间件将该传输方式视为内部通道，因此未对其应用与外部请求相同的认证上下文。 在依赖“按用户授权”来隔离线程（threads）和运行（runs）的部署环境中，一个已认证用户可以将 Webhook

CVSS 5.9 · Medium

Possible ATT&CK Techniques 1 AI

T1200 · Hardware Additions
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-55235

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication
Source: CVE Program / CVE List V5
Vulnerability Description
langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that transport as internal without applying the authentication context used for external requests. In deployments that rely on per-user authorization to separate threads and runs, an authenticated user can direct a webhook to the server's own thread and run routes, allowing creation of a run on or modification of another user's thread and limited incorporation of the targeted thread's metadata into the created run record. The affected path requires webhook targets and per-user authorization boundaries; deployments that deliberately re-enable loopback delivery should restrict it to controlled same-process routes because those webhooks remain unauthenticated. This issue is fixed in version 0.10.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L
Source: CVE Program / CVE List V5
Vulnerability Type
认证机制不恰当
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
langchain-ai langgraph-api < 0.10.0 -

II. Public POCs for CVE-2026-55235

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-55235

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-55235 (1)

Same Patch Batch · langchain-ai · 2026-09-14 · 3 CVEs total

CVE-2026-55253 7.7 HIGH LangChain MongoDB: NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant
CVE-2026-55236 5.9 MEDIUM langgraph-api: Incomplete assistant authorization in LangGraph Server run creation

IV. Related Vulnerabilities

Same product: langgraph-api
Same vendor: langchain-ai
Same weakness: CWE-287

V. Comments for CVE-2026-55235

No comments yet

Leave a comment