Cyber Resilience

CVE-2025-46560

Vllm 0.8.0 – 0.8.5

Public PoC
Published
30 April 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 0.0049 39th percentile
Risk Priority 53 floored blend · peak EPSS

Summary

CVE-2025-46560 is a medium-severity Inefficient Regular Expression Complexity (CWE-1333) 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 39th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Adversarial Attacks risk domain.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-15 (Development Process, Standards, and Tools) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

vLLM is a high-throughput inference and serving engine for large language models. Versions 0.8.0 through 0.8.4 contain a performance vulnerability in the multimodal tokenizer's input preprocessing logic. The affected code replaces placeholder tokens such as <|audio_|> and <|image_|> by repeatedly concatenating tokens according to precomputed lengths; the use of inefficient list operations produces quadratic time complexity, enabling an attacker to supply specially crafted inputs that trigger excessive CPU and memory consumption.

An authenticated remote attacker with low privileges can submit malicious multimodal prompts to the inference engine. Because the vulnerability affects only availability, successful exploitation results in resource exhaustion that can degrade or deny service to other users without disclosing data or altering model behavior.

The issue is resolved in vLLM 0.8.5. The project security advisory GHSA-vc6m-hm49-g9qg and the corresponding code change in phi4mm.py document the patch that replaces the quadratic concatenation pattern with an efficient implementation.

The vulnerability is specific to multimodal LLM workloads and carries a CVSS score of 6.5 with a high availability impact. EPSS remains low, with a recorded peak of 0.0152.

EU & UK References

Vulnerability Data

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces…

more

placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to ​​inefficient list concatenation operations​​, the algorithm exhibits ​​quadratic time complexity (O(n²))​​, allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Adversarial Attacks
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.
T1499.003 Application Exhaustion Flood Impact
Adversaries may target resource intensive features of applications to cause a denial of service (DoS), denying availability to those applications.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-48887Same product: Vllm Vllm
CVE-2025-71379Same product: Vllm Vllm
CVE-2026-55574Same product: Vllm Vllm
CVE-2026-54233Same product: Vllm Vllm
CVE-2025-48956Same product: Vllm Vllm
CVE-2025-48942Same product: Vllm Vllm
CVE-2025-48943Same product: Vllm Vllm
CVE-2026-34755Same product: Vllm Vllm
CVE-2025-30202Same product: Vllm Vllm
CVE-2025-29770Same product: Vllm Vllm

Affected Assets

vllm
vllm
0.8.0 — 0.8.5

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

Developer testing and evaluation can discover inefficient regex patterns via performance or static analysis.

Development standards and tools can require safe regex construction and forbid known exponential patterns.

Denial-of-service protections limit resource exhaustion caused by expensive regex evaluation.

Input validation can constrain data that would otherwise trigger worst-case regex complexity.

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 directly prevent inefficient regex via reviews, static analysis, and safe libraries.

ID.RA-01 partial match
prevents

Vulnerability identification processes can discover ReDoS issues in existing code but do not stop their introduction.

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 and reject regex patterns with exponential worst-case complexity.

prevents

Secure development lifecycle mandates review of algorithmic efficiency, directly addressing ReDoS-prone regex.

prevents

Application security requirements can specify input-validation rules that limit regex complexity.

prevents

Secure architecture principles encourage avoidance of computationally expensive constructs such as catastrophic backtracking.

prevents

Secure coding standards explicitly prohibit or limit the use of inefficient regular expressions.

References