What’s Vulnerable › Vulnerabilities

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

• Severity: high (CVSS 8.1 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.9% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-09-04 · updated 2026-09-10
• Weakness: CWE-94

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

• lavague-ai LaVague: through 0.2.35

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

Get alerted when CVE-2026-85694 or the next vulnerability affects your stack