CVE-2026-85694: Improper Control of Generation of Code ('Code Injection') in lavague-ai LaVague
Description
LaVague version 0.2.35 and earlier contain a critical remote code execution vulnerability in the PythonFromMarkdownExtractor.extract_as_object function. This flaw allows attackers to inject malicious Python code via untrusted language model output derived from web page content, leading to arbitrary code execution on the host without operator review.
CVSS v4.0
Score 9.2critical
Affected software
lavague-ai
LaVague
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-85694 is a remote code execution vulnerability in LaVague (versions up to and including 0.2.35) within the PythonFromMarkdownExtractor.extract_as_object method. The vulnerability arises because this method evaluates untrusted language model output that originates from web page content. Attackers can exploit this by injecting malicious Python code through indirect prompt injection techniques, causing arbitrary code execution on the operator's host environment without any review or validation.
Potential Impact
Successful exploitation allows remote attackers to execute arbitrary Python code on the host system running LaVague, potentially leading to full system compromise. The vulnerability is critical with a CVSS 4.0 base score of 9.2, indicating high impact and complexity. There are no known exploits in the wild at this time.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, avoid processing untrusted web page content with the affected function or restrict usage to trusted inputs only.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-09-04T13:51:51.559Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a9adb49acd9273b49bef5fc
Added to database: 09/04/2026, 14:52:57 UTC
Last enriched: 09/15/2026, 00:56:03 UTC
Last updated: 10/18/2026, 06:48:20 UTC
Views: 82
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.