CVE-2025-48943
MEDIUMDescription
vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.
Is your site exposed to CVE-2025-48943?
Run a free security scan — no signup, results in seconds.
CVSS v3.1 Score
Weakness Type (CWE)
Affected Products
| Vendor | Product |
|---|---|
| vllm | vllm |
References
Frequently Asked Questions
What is CVE-2025-48943? +
How severe is CVE-2025-48943? +
What products are affected by CVE-2025-48943? +
How do I check if I'm vulnerable to CVE-2025-48943? +
Related Vulnerabilities
The MCP Python SDK, called `mcp` on PyPI, is a Python implementation of the Model Context Protocol (MCP). Prior to …
RaTeX is a KaTeX-compatible math rendering engine written in Rust. Prior to version 0.1.11, the public parser entrypoint `ratex_parser::parse(&str)` panics …
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 …
A weakness in Automated Logic and Carrier i-Vu Gen5 router on driver version drv_gen5_106-01-2380, allows malformed packets to be sent …
NanaZip is the 7-Zip derivative intended for the modern Windows experience. Prior to 6.5.1749.0, NanaZip's .NET single-file bundle handler in …