Cyber Resilience

CVE-2025-48943

Vllm 0.8.0 – 0.9.0

Published
30 May 2025
Modified
17 June 2026
Patch / advisory
CVSS Score v3.1 6.5
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS Score 0.0042 35th percentile
Risk Priority 50 floored blend · peak EPSS

Summary

CVE-2025-48943 is a medium-severity Uncaught Exception (CWE-248) vulnerability in Vllm Vllm. Its CVSS base score is 6.5 (Medium).

Operationally, exploitation aligns with the MITRE ATT&CK technique Endpoint Denial of Service (T1499); ranked at the 35th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as NLP and Transformers; in the LLM/Generative AI Risks risk domain.

The strongest mitigations our analysis identified map to SA-8 (Security and Privacy Engineering Principles) and SC-24 (Fail in Known State) — see the control section below for these in your framework.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

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…

more

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.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llms, vllm

Related Threats

MITRE ATT&CK Enterprise Techniques

T1499 Endpoint Denial of Service Impact
Adversaries may perform Endpoint Denial of Service (DoS) attacks to degrade or block the availability of services to users.
T1499.004 Application or System Exploitation Impact
Adversaries may exploit software vulnerabilities that can cause an application or system to crash and deny availability to users.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-48942Same product: Vllm Vllm
CVE-2026-55514Same product: Vllm Vllm
CVE-2025-46560Same product: Vllm Vllm
CVE-2025-48887Same product: Vllm Vllm
CVE-2025-48956Same product: Vllm Vllm
CVE-2025-62426Same product: Vllm Vllm
CVE-2026-34755Same product: Vllm Vllm
CVE-2026-22773Same product: Vllm Vllm
CVE-2025-30202Same product: Vllm Vllm
CVE-2025-29770Same product: Vllm Vllm

Affected Assets

vllm
vllm
0.8.0 — 0.9.0

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

Security engineering principles include robust exception management to keep the system in a defined state.

Fail-in-known-state reduces the impact when an uncaught exception occurs by preserving a safe condition.

Error handling requirements force structured catching and response to exceptions instead of allowing them to propagate uncaught.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match
prevents

Secure SDLC practices explicitly require structured exception handling to prevent uncaught exceptions from reaching production.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Security testing can detect uncaught exceptions before production deployment.

prevents

Secure development lifecycle includes exception-handling standards that reduce uncaught exceptions.

prevents

Application security requirements typically mandate robust error and exception handling.

prevents

Secure architecture principles call for centralized, comprehensive exception management.

prevents

Secure coding standards directly require catching and handling exceptions to prevent crashes or leaks.

References