CVE-2026-85694 LaVague 0.2.35 Remote Code Execution via eval extraction
CriticalCVSS 9.2
EPSS 0.94%
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: no · technical impact: total
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.
Upgrade path
1 package: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| pypi lavague-core | <= 0.2.35 | after 0.2.35 | Fixed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| pypi lavague-core | <= 0.2.35 | No fix listed |
References
- GitHub Issue #650 exploit issue-tracking
- github.com product
- github.com technical-description
- VulnCheck Advisory: LaVague 0.2.35 Remote Code Execution via eval extraction third-party-advisory
- ENISA EUVD EUVD-2026-71143 third-party-advisory