CVE-2025-48942
MEDIUMDescription
vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.
Is your site exposed to CVE-2025-48942?
Run a free security scan — no signup, results in seconds.
CVSS v3.1 Score
Weakness Type (CWE)
Affected Products
| Vendor | Product |
|---|---|
| vllm | vllm |
References
Advisories & Patches
Other References
Frequently Asked Questions
What is CVE-2025-48942? +
How severe is CVE-2025-48942? +
What products are affected by CVE-2025-48942? +
How do I check if I'm vulnerable to CVE-2025-48942? +
Related Vulnerabilities
go-ethereum (geth) is a golang execution layer implementation of the Ethereum protocol. A vulnerable node can be forced to shutdown/crash …
tRPC allows users to build & consume fully typesafe APIs without schemas or code generation. In versions starting from 11.0.0 …
Multer is a node.js middleware for handling `multipart/form-data`. A vulnerability that is present starting in version 1.4.4-lts.1 and prior to …
The MCP Python SDK, called `mcp` on PyPI, is a Python implementation of the Model Context Protocol (MCP). Prior to …
The MCP Python SDK, called `mcp` on PyPI, is a Python implementation of the Model Context Protocol (MCP). Prior to …
@builder.io/qwik-city is the meta-framework for Qwik. When a Qwik Server Action QRL is executed it dynamically load the file containing …