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.
No analysis available yet.
Remediation
No remediation available yet.
Tracking
Sign in to view the affected projects.
Advisories
No advisories yet.
References
History
Fri, 04 Sep 2026 14:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | LaVague 0.2.35 Remote Code Execution via eval extraction | |
| Weaknesses | CWE-94 | |
| References |
| |
| Metrics |
cvssV3_1
|
Subscriptions
No data.
Status: PUBLISHED
Assigner: VulnCheck
Published:
Updated: 2026-09-04T14:32:37.407Z
Reserved: 2026-09-04T13:51:51.559Z
Link: CVE-2026-85694
No data.
Status : Received
Published: 2026-09-04T15:17:47.540
Modified: 2026-09-04T15:17:47.540
Link: CVE-2026-85694
No data.
OpenCVE Enrichment
No data.
Weaknesses
-
CWE-94
Improper Control of Generation of Code ('Code Injection')