CVE-2025-48944
MEDIUM EPSS 35.9%
Published May 30, 20251y ago · Modified Jun 17, 20261w ago
6.5 CVSS 3.1
Published May 30, 2025 1y ago
Last Modified Jun 17, 2026 1w ago
Description
vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference worker with a single request. The worker will remain down until it is restarted. Version 0.9.0 fixes the issue.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Attack Vector Network
Attack Complexity Low
Privileges Required Low
User Interaction None
Scope Unchanged
Confidentiality None
Integrity None
Availability High
Threat Intelligence
EPSS Exploit Probability
35.9% percentile
Exploit & Patch Status
Public Exploit Known
No Patch Available
Weaknesses 1
CWE-20 Improper Input Validation Validation
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| vllm | vllm | * | ≥0.8.0 – <0.9.0 |
References 2
- github.com https://github.com/vllm-project/vllm/pull/17623
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-vrq3-r879-7m65
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.