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

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-55253— LangChain MongoDB: NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant data exposure

Quick assessment

Affected
langchain-ai langchain-mongodb
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.

LangChain MongoDB 提供了 MongoDB、Atlas、LangChain 和 LangGraph 之间的集成。在 langgraph-checkpoint-mongodb 0.3.0 和 langgraph-store-mongodb 0.4.0 之前， 、 以及 方法在将过滤字典合并到 MongoDB 查询时，未递归地拒绝以 为前缀的键。 这意味着，能够通过 HTTP 查询参数、请求体字段或代理（agent）工具参数控制过滤参数的已认证调用者，可以注入 MongoDB 查询语言（MongoDB

CVSS 7.7 · High

Affected Version Matrix 3

VendorProduct Version RangeStatus
langchain-ai langchain-mongodb < 0.4.0 affected
langchain-ai langgraph-checkpoint-mongodb < 0.3.0 affected
langchain-ai langgraph-store-mongodb < 0.4.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-55253

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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
LangChain MongoDB: NoSQL Operator Injection in MongoDBSaver.list() leading to cross-tenant data exposure
Source: CVE Program / CVE List V5
Vulnerability Description
LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0, MongoDBSaver.list(), MongoDBSaver.alist(), and MongoDBStore.search() incorporate filter dictionaries into MongoDB queries without recursively rejecting keys prefixed with $. An authenticated caller who controls a filter argument through HTTP query parameters, request body fields, or agent tool arguments can inject MongoDB Query Language operators such as $regex or $where. In a multi-tenant deployment that uses the filter to enforce per-user or per-tenant isolation, injected operators can bypass intended equality filtering and expose other tenants' checkpoint or store data. Filters constructed entirely from trusted server-side values have lower practical risk. This issue is fixed in langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
数据查询逻辑中特殊元素的不当中和
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
langchain-ai langchain-mongodb < 0.4.0 -
langchain-ai langgraph-checkpoint-mongodb < 0.3.0 -
langchain-ai langgraph-store-mongodb < 0.4.0 -

II. Public POCs for CVE-2026-55253

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-55253

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-55253 (5)

Vendor Advisories for CVE-2026-55253 (1)

Vendor Pages for CVE-2026-55253 (1)

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

CVE-2026-55235 5.9 MEDIUM langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes wi
CVE-2026-55236 5.9 MEDIUM langgraph-api: Incomplete assistant authorization in LangGraph Server run creation

IV. Related Vulnerabilities

Same vendor: langchain-ai
Same weakness: CWE-943

V. Comments for CVE-2026-55253

No comments yet

Leave a comment