- CVSS
- HIGH · 8.1v3.1CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
- Published
- 2026-09-04
- Weakness
- CWE-94
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-85694
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.
References
- https://github.com/lavague-ai/LaVague
- https://github.com/lavague-ai/LaVague/blob/9024bb83/lavague-core/lavague/core/extractors.py
- https://github.com/lavague-ai/LaVague/issues/650
- https://www.vulncheck.com/advisories/lavague-0.2.35-remote-code-execution-via-eval-extraction
- https://github.com/lavague-ai/LaVague/issues/650
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-85694 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.