Vulnerability · Published Sep 4, 2026 · Assigned by VulnCheck
CVE-2026-85694LaVague 0.2.35 Remote Code Execution via eval extraction
High 8.1
In plain English
A high-severity code injection in LaVague from lavague-ai. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.9% (higher than 61% of all known vulnerabilities).
Severity (CVSS 3.1)8.1High
Exploit odds (30 days)0.9%top 38.8% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known
Official 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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| lavague-ai | LaVague | 0 – through 0.2.35 |
Weakness: CWE-94 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
References
- GitHub Issue #650 issue-tracking
- https://github.com/lavague-ai/LaVague product
- https://github.com/lavague-ai/LaVague/blob/9024bb83/lavague-core/lavague/core/extractors.py technical-description
- VulnCheck Advisory: LaVague 0.2.35 Remote Code Execution via eval extraction third-party-advisory