LaVague 0.2.35 Remote Code Execution via eval extraction
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- High
- Attack requirements
- Present
- Impact type
- Code execution
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- No fix listed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-94.
Summary
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| lavague-ai | LaVague | up to 0.2.35 | — | No fix listed | CNA |
- LaVague Vendorlavague-ai Affected up to 0.2.35 Fixed in — No fix listed CNA
Remediation
No fixed version listed by the sources yet.
Timeline
- 2026-10-02 Threatist record created from CVE-2026-85694
- 2026-10-03 Alias added: GHSA-gvgx-3mw6-m592
References
Sources
- CVE-2026-85694 · CVE Program
- CVE-2026-85694 · NVD
- FIRST EPSS
- GHSA-gvgx-3mw6-m592 · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences