CVE-2025-46560Network attack vector

Service interruption via quadratic placeholder expansion

Published Apr 30, 2025 · Updated Apr 30, 2025

Resource exhaustion in vLLM 0.8.0 through 0.8.4 allows remote authenticated users to interrupt inference service via crafted multimodal input. The input_processor_for_phi4mm function repeatedly concatenates placeholder-token expansions into a growing list, producing quadratic preprocessing work. Access to an inference endpoint that accepts Phi-4 multimodal requests is required, and the reported consequence is service resource exhaustion rather than data access or modification.

CVSS severity6.5
Medium
EPSS probability0.50%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Resource exhaustion in vLLM 0.8.0 through 0.8.4 allows remote authenticated users to interrupt inference service via crafted multimodal input. The input_processor_for_phi4mm function repeatedly concatenates placeholder-token expansions into a growing list, producing quadratic preprocessing work. Access to an inference endpoint that accepts Phi-4 multimodal requests is required, and the reported consequence is service resource exhaustion rather than data access or modification.

The record

CVE
CVE-2025-46560
Published
Apr 30, 2025
Updated
Apr 30, 2025
Vendor
vLLM Project
Product
vLLM
Classifications
CWE-1333, T1499.004
Attack vector
network
Privileges
authenticated

Timeline

How it unfolded

  1. Apr 30, 2025CVE publishedPublication date reported by the CVE source.
  2. Apr 30, 2025Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=>= 0.8.0, < 0.8.5

What conditions does exploitation require?

Attack vectornetwork
Required privilegesauthenticated

What is affected?

vLLM Project · vLLMversion=>= 0.8.0, < 0.8.5

Published CVSS scores

6.5GitHub, Inc.CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
7.5NIST NVDCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-1333Inefficient Regular Expression Complexity
T1499.004Application or System Exploitation

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo