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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-85694— LaVague 0.2.35 Remote Code Execution via eval extraction

Quick assessment

Affected
lavague-ai LaVague
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.

lavague是lavague团队的一个用于开发人工智能网络代理的模型框架。 lavague 0.2.35及之前版本存在代码注入漏洞，该漏洞源于PythonFromMarkdownExtractor.extract_as_object方法评估了来自网页内容的不可信语言模型输出，可能允许攻击者通过间接提示注入向网页中注入恶意Python代码，从而在操作者主机上执行任意代码。

CVSS 8.1 · High EPSS 0.94% · P61

Affected Version Matrix 1

VendorProduct Version RangeStatus
lavague-ai LaVague ≤ 0.2.35 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-85694

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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
LaVague 0.2.35 Remote Code Execution via eval extraction
Source: CVE Program / CVE List V5
Vulnerability Description
LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extract_as_object that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute arbitrary code on the operator's host without review.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
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
lavague 代码注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
lavague是lavague团队的一个用于开发人工智能网络代理的模型框架。 lavague 0.2.35及之前版本存在代码注入漏洞，该漏洞源于PythonFromMarkdownExtractor.extract_as_object方法评估了来自网页内容的不可信语言模型输出，可能允许攻击者通过间接提示注入向网页中注入恶意Python代码，从而在操作者主机上执行任意代码。
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
lavague-ai LaVague 0 ~ 0.2.35 -

II. Public POCs for CVE-2026-85694

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-85694

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-85694 (1)

Security Blog Posts for CVE-2026-85694 (1)

Other References for CVE-2026-85694 (1)

IV. Related Vulnerabilities

Same weakness: CWE-94

V. Comments for CVE-2026-85694

No comments yet

Leave a comment