EUVD-2026-71143
GHSA-gvgx-3mw6-m592
Severity by source
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Network-reachable via web content with no auth or interaction (AV:N/PR:N/UI:N), but reliably steering a non-deterministic LLM into a working payload raises complexity (AC:H); eval yields full host compromise (C/I/A:H).
Primary rating from Vendor (VulnCheck).
CVSS VectorVendor: VulnCheck
Lifecycle Timeline
2DescriptionCVE.org
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.
Articles & Coverage 1
AnalysisAI
Remote code execution in LaVague 0.2.35, an LLM-driven web-automation agent framework, arises because PythonFromMarkdownExtractor.extract_as_object evaluates language-model output that is derived from attacker-influenced web page content. An attacker who controls or poisons a page the agent visits can use indirect prompt injection to coerce the model into emitting Python that is then eval'd and executed on the operator's host with no human review. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Requires that the operator run a LaVague agent (0.2.35) that fetches and processes attacker-influenced web page content, and that the content reach the PythonFromMarkdownExtractor.extract_as_object code path where model output is eval'd. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The CVSS 4.0 vector (AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H, base 9.2) captures the core tension: impact is full compromise of the host (confidentiality, integrity, availability all High) and no authentication or user interaction is required, but exploitation is probabilistic - AC:H and AT:P reflect that the attacker must reliably steer a non-deterministic LLM into producing exactly the malicious code that survives extraction and reaches eval(). … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | Full exploit scenario with step-by-step reproduction available after sign-in. |
| Remediation | No vendor-released patched version is identified in the available data - the references point to the vulnerable source and a tracking issue (GitHub #650) rather than a tagged fixed release, so no fix version can be cited. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours, conduct a complete inventory of all systems running LaVague 0.2.35 or related versions, isolate them from production networks if operationally feasible, and review access logs to identify all websites the agents have contacted. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Wazuh SIEM platform versions 4.4.0 through 4.9.0 contain an unsafe deserialization vulnerability in the DistributedAPI t
BentoML version 1.4.2 and earlier contains an unauthenticated remote code execution vulnerability through insecure deser
pgAdmin 4 contains critical remote code execution vulnerabilities in the Query Tool download and Cloud Deployment endpoi
The renderLocalView function in render/views.py in graphite-web in Graphite 0.9.5 through 0.9.10 uses the pickle Python
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Rated critica
OpenSSL before 0.9.8za, 1.0.0 before 1.0.0m, and 1.0.1 before 1.0.1h does not properly restrict processing of ChangeCiph
pyLoad download manager version prior to 0.5.0b3.dev77 exposes the Flask SECRET_KEY through an unauthenticated endpoint.
Langflow (a visual LLM pipeline builder) contains a critical unauthenticated code execution vulnerability (CVE-2026-3301
In Mercurial before 4.1.3, "hg serve --stdio" allows remote authenticated users to launch the Python debugger, and conse
Unauthenticated remote code execution affects Kestra OSS (the open-source event-driven orchestration platform) prior to
Unauthenticated remote code execution in Marimo ≤0.20.4 allows attackers to execute arbitrary system commands via the `/
pyLoad is the free and open-source Download Manager written in pure Python. Rated medium severity (CVSS 5.3), this vulne
Same weakness CWE-94 – Code Injection
View allShare
External POC / Exploit Code
Leaving vuln.today