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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-33873— Langflow has Authenticated Code Execution in Agentic Assistant Validation

Quick assessment

Affected
langflow-ai langflow
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.

Langflow是Langflow开源的一个用于构建多代理和 RAG 应用程序的可视化框架。 Langflow 1.9.0之前版本存在代码注入漏洞，该漏洞源于Agentic Assistant功能在验证阶段执行LLM生成的Python代码，可能导致任意服务器端Python代码执行。

AI Predicted 8.8 Difficulty: Easy EPSS 1.82% · P78
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-33873

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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
Langflow has Authenticated Code Execution in Agentic Assistant Validation
Source: CVE Program / CVE List V5
Vulnerability Description
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class server-side. In deployments where an attacker can access the Agentic Assistant feature and influence the model output, this can result in arbitrary server-side Python execution. Version 1.9.0 fixes the issue.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N
Source: CVE Program / CVE List V5
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Source: CVE Program / CVE List V5
Vulnerability Title
Langflow 代码注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Langflow是Langflow开源的一个用于构建多代理和 RAG 应用程序的可视化框架。 Langflow 1.9.0之前版本存在代码注入漏洞，该漏洞源于Agentic Assistant功能在验证阶段执行LLM生成的Python代码，可能导致任意服务器端Python代码执行。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
langflow-ai langflow < 1.9.0 -

II. Public POCs for CVE-2026-33873

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-33873

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-33873 (11)

Vendor Advisories for CVE-2026-33873 (1)

Other References for CVE-2026-33873 (4)

Same Patch Batch · langflow-ai · 2026-03-27 · 6 CVEs total

CVE-2026-5027 8.8 HIGH Langflow - Path Traversal Arbitrary File Write via upload_user_file
CVE-2026-5025 6.5 MEDIUM Langflow - Application Logs Exposed to All Authenticated Users
CVE-2026-5022 Langflow - Missing Authorization on download_image Endpoint
CVE-2026-5026 Langflow - Stored XSS via Malicious SVG Upload
CVE-2026-34046 Langflow: Authenticated Users Can Read, Modify, and Delete Any Flow via Missing Ownership

IV. Related Vulnerabilities

Same product: langflow
Same vendor: langflow-ai
Same weakness: CWE-94

V. Comments for CVE-2026-33873

No comments yet

Leave a comment