// For flags

CVE-2025-48944

vLLM Tool Schema allows DoS via Malformed pattern and type Fields

Severity Score

6.5
*CVSS v3.1

Exploit Likelihood

*EPSS

Affected Versions

*CPE

Public Exploits

0
*Multiple Sources

Exploited in Wild

-
*KEV

Decision

Track*
*SSVC
Descriptions

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.

*Credits: N/A
CVSS Scores
Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High
Attack Vector
Network
Attack Complexity
Low
Authentication
Single
Confidentiality
None
Integrity
None
Availability
Complete
* Common Vulnerability Scoring System
SSVC
  • Decision:Track*
Exploitation
Poc
Automatable
No
Tech. Impact
Partial
* Organization's Worst-case Scenario
Timeline
  • 2025-05-28 CVE Reserved
  • 2025-05-30 CVE Published
  • 2025-05-30 CVE Updated
  • 2025-08-06 EPSS Updated
  • ---------- Exploited in Wild
  • ---------- KEV Due Date
  • ---------- First Exploit
CWE
  • CWE-20: Improper Input Validation
CAPEC
Affected Vendors, Products, and Versions
Vendor Product Version Other Status
Vendor Product Version Other Status <-- --> Vendor Product Version Other Status
Vllm-project
Search vendor "Vllm-project"
 Vllm
Search vendor "Vllm-project" for product "Vllm"
 >= 0.8.0 < 0.9.0
Search vendor "Vllm-project" for product "Vllm" and version " >= 0.8.0 < 0.9.0"
en
Affected