CVE-2026-85694 LaVague 0.2.35 Remote Code Execution via eval extraction
Attackers can execute arbitrary code on the host by injecting malicious Python via web content processed by the LaVague library.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-85694?
CVE-2026-85694 is a critical code injection vulnerability in lavague-ai LaVague, published on 4 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
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.
Weakness: CWE-94
Which versions are affected by CVE-2026-85694?
How do I fix CVE-2026-85694?
No fix has been published for CVE-2026-85694 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-85694 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-85694 exists.
Sources
Also known as GHSA-gvgx-3mw6-m592.