by Kastro
Paper/Archive/CVE-2026-85694

CVE-2026-85694

lavague-ai LaVague — LaVague 0.2.35 Remote Code Execution via eval extraction

EPSS 0.9%public exploitCVSS 9.2
critical.is priorityof 100
50
CVSS 9.2 (CNA)9.2 / 10 × 3027.6Not in CISA KEV+300.0EPSS percentile 61.0.610 × 2012.2Exploit: SSVC poc+1010.0SSVC exploitation: poc+100.0
Description · from the CVE record

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

ProductAffectedFixed inSource
LaVague≤ 0.2.35–CNA

Scores by source

VulnCheck (CNA)9.2CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
VulnCheck (CNA)8.1CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
CISA ADPSSVCExploitation: poc · Automatable: no · Technical impact: total

References

exploitgithub.com/lavague-ai/LaVague/issues/650refgithub.com/lavague-ai/LaVaguewriteupgithub.com/lavague-ai/LaVague/blob/9024bb83/lavague-core/lavague/core/extractors.pywriteupvulncheck.com/advisories/lavague-0.2.35-remote-code-execution-via-eval-extraction