CVE-2026-85694

published 4 Sep 2026 · updated 8 Sep 2026

LaVague 0.2.35 Remote Code Execution via eval extraction

8.1HighCVSS 8.1EPSS 1%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 1%. No fixed version is recorded.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
lavague-ai<=0.2.35

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-85694 severity on Zeptric[![CVE-2026-85694](https://zeptric.io/badge/cve/CVE-2026-85694.svg)](https://zeptric.io/cve/CVE-2026-85694)