CVE-2025-9141

CVE-2025-9141 is a publicly disclosed cybersecurity vulnerability assigned a Common Vulnerabilities and Exposures identifier by the National Institute of Standards and Technology. For AI governance and compliance, tracking specific CVEs is critical because vulnerabilities in AI infrastructure, model deployment systems, or data processing pipelines can expose sensitive training data or compromise model integrity. Organizations must monitor CVE databases and assess whether disclosed vulnerabilities affect their AI systems, then prioritize remediation based on risk and implement appropriate security controls to maintain compliance with data protection regulations.

1 item

ResearchGlobal2026-08-24

CVE-2025-9141 Makes Inference Engines a Governed Security Dependency

Independent security research published in August 2026 documents a concrete attack class in which a malicious LLM could exploit vulnerabilities in its own inference engine to execute arbitrary code on the host machine. The analysis cites CVE-2025-9141, an arbitrary-code-execution bug in vLLM's tool parser that was merged despite automated critical-severity warnings. Organizations self-hosting open-weight models are advised to separate GPU and token-parsing hosts and treat all inference engine output as untrusted.

vLLM SGLang inference engine security arbitrary code execution self-hosted AI supply chain security CVE-2025-9141 open-weight models