HighCVE-2026-100650

vLLM before 0.29.0 Resource Exhaustion via Unbounded Media Materialization (CVE-2026-100650)

Published 26.09.2026Last modified 06.10.2026Sources: Red Hat, CVE.org, OSV, BSI

What is affected, what to do

A flaw was found in vLLM. The system fully downloads and decodes remote or embedded media files before enforcing configured size and quantity restrictions.

Update vLLM to version 0.29.0.

Affected: vLLM lt *..0.29.0
Fixed in: vLLM 0.29.0

Not sure whether and how you are affected? Ask a question about this vulnerability

Metrics

7.1

Priority

XIEM Effective CVSS: highest available CVSS rating from NVD and vendor data.

Source: Vendor (CNA), CVSS v4

6.5

CVSS v3

Severity Medium on the scale from 0 to 10.

Source: Red Hat, CVE.org, OSV, BSI

0.8 %

EPSS score

Low — model estimates < 1% exploitation likelihood.

Source: FIRST EPSS, percentile 57.1

Show all metrics

Severity: High
Priority (0–325) The priority score is a consolidated metric that condenses several individual signals into a single, action-guiding ranking: technical severity (CVSS), exploitation likelihood (EPSS), known-exploited status (KEV) and the context of the affected asset. The aim is to answer the only truly important question in vulnerability management: what first? Read in glossary: 88.90 Methodology
Exploit maturity An exploit is code or a technique that specifically uses a concrete vulnerability to force unintended behaviour — such as executing code or escalating privileges. It is the tool that turns a theoretical flaw into a practical attack. Read in glossary: no public PoC known
XIEM Effective CVSS XIEM® is the tiered managed-security operating model from NEOSEC and a registered trademark of NEOSEC GmbH. It extends classic SIEM — the central collection, normalisation and correlation of security-relevant events — with endpoint forensics, network visibility and deception technology, and consolidates them into three building tiers: Sentry, Orchestrate and Command. Read in glossary: 7.1 Methodology
CVSS v3 CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions. Read in glossary: 6.5
CVSS v4 CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions. Read in glossary: 7.1
EPSS score The EPSS score is the absolute model output for an individual vulnerability: the estimated probability of real-world exploitation within the next 30 days, expressed as a value between 0 and 1 (i.e. 0 % to 100 %). A score of 0.42 means „the model estimates a 42 % chance of real-world exploitation within 30 days“. Read in glossary: 0.8 %; Low — model estimates < 1% exploitation likelihood.
EPSS percentile The EPSS percentile is the relative position of a vulnerability within all EPSS-scored CVEs, expressed as a value between 0 and 1. A percentile of 0.90 means „this CVE has a higher EPSS score than 90 % of all other scored CVEs“. Unlike the EPSS score, it is not a probability — but a positioning within a ranking. Read in glossary: 57.1; High — this CVE ranks above the median of all CVEs scored today (rank ≥ 36%).
KEV status The KEV catalogue is a list maintained by the US authority CISA of vulnerabilities for which active exploitation in the wild has been confirmed. It answers not the question „how severe?“ but „is it already being attacked?“ — thereby sharply prioritising patching. Read in glossary: —
Published: 26.09.2026
CISA assessment (SSVC): Exploitation: proof of concept · not automatable · Technical impact: partial; Source: CISA Vulnrichment, as of 30 September 2026
CWE CWE is a catalogue of typical weakness types in software and hardware — such as flawed input validation, unsafe memory handling or poor authentication. Where a CVE names a concrete vulnerability in a concrete product, a CWE describes the underlying class of defect. Read in glossary: CWE-400

Detection rules

No NEOSEC detection rule is available for this vulnerability yet.

Classification under NIS2 and CRA

Rule-based classification from exploitation status and severity. It does not replace a case-by-case assessment.

NIS2 NIS2 is EU Directive (EU) 2022/2555 to raise the level of cybersecurity across the Union. It substantially broadens obligations compared with the first NIS directive: more sectors, mandatory risk management, staged reporting duties and personal accountability of senior management. Read in glossary: High technical severity: assess and remediate the vulnerability in vulnerability handling under Art. 21(2)(e) NIS2 and document the decision.
CRA The CRA is EU Regulation (EU) 2024/2847 setting horizontal cybersecurity requirements for „products with digital elements“ — from industrial controllers and software to connected consumer devices. For the first time manufacturers must ensure security across the entire product lifecycle, handle vulnerabilities and provide security updates. Read in glossary: From 11.12.2027, Annex I Part II CRA requires manufacturers of affected products with digital elements to handle vulnerabilities without delay and provide security updates.
ISO/IEC 27001 ISO/IEC 27001 is the internationally leading standard for an information security management system (ISMS). It describes a risk-based, process-oriented framework to systematically plan, implement, review and improve information security. Read in glossary: Control A.8.8, management of technical vulnerabilities: assess relevance to your systems, plan remediation and keep evidence.

Description

A flaw was found in vLLM. The system fully downloads and decodes remote or embedded media files before enforcing configured size and quantity restrictions. A remote attacker can exploit this vulnerability by submitting requests containing excessively large or numerous media payloads, forcing the server to consume excessive memory and network bandwidth. This resource exhaustion can lead to a Denial of Service (DoS), rendering the service unresponsive or causing it to crash.

Source: redhat_csaf, NVD (NIST), OSV (Open Source Vulnerabilities), cvelistv5, BSI WID Portal, BSI CSAF

Affected products

The following versions are affected. Older releases of the same product line are also vulnerable unless stated otherwise.

Affected products
		Affected versions	Fixed in
vllm-project	vllm	`< 0.29.0`	`0.29.0`
vllm	vllm	`≤ 0.29.0`	—
Open Source	vllm	`< 0.29.0`	`0.29.0`
pypi	vllm	`0.14.1` `0.6.1` `0.8.3` `0.6.5` `0.22.1` `0.13.0` `0.12.0` `0.2.2` `0.25.0` `0.6.1.post1` `0.19.1` `0.27.1` `0.1.0` `0.10.1` `0.3.1` `0.6.0` `0.7.0` `0.7.1` `0.2.7` `0.1.2` `0.6.3.post1` `0.9.0` `0.11.2` `0.6.1.post2` `0.3.3` `0.6.6` `0.4.0.post1` `0.5.4` `0.2.5` `0.1.1` `0.2.6` `0.5.3.post1` `0.9.2` `0.11.1` `0.24.0` `0.4.1` `0.18.0` `0.19.0` `0.14.0` `0.7.3` `0.3.0` `0.8.1` `0.17.0` `0.4.3` `0.2.1`	— — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — —

Vendors and products

Weakness classes (CWE)

CWE-400Uncontrolled Resource Consumption
Class
The product does not properly control the allocation and maintenance of a limited resource.
Entry at MITRE CWE-400

References & sources

github.comGitHub Security Advisory (GHSA-p6g9-7v3x-m8mv)Vendor advisory
github.comPatch CommitPatch
vulncheck.comVulnCheck Advisory: vLLM before 0.29.0 Resource Exhaustion via Unbounded Media MaterializationThird-party advisory

Changes to this CVE

Who changed this CVE and when: NVD (analysis, affected products, CVSS), the CVE publisher (CNA) and additional providers such as CISA (ADP).

06.10.2026Initial analysis by NVDNVD

Newly listed as affected:

vLLM (through 0.29.0)

New references:

Show 5 original changes

Individual changes of this event as published by NVD
Type	Action	Before	After
Product configuration	added	—	OR cpe:2.3:a:vllm:vllm::::::::* versions up to (including) 0.29.0
Reference type	added	—	VulnCheck: https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34 Types: Patch
Reference type	added	—	VulnCheck: https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv Types: Exploit, Mitigation, Vendor Advisory
Reference type	added	—	VulnCheck: https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization Types: Third Party Advisory
Reference type	added	—	CISA-ADP: https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv Types: Exploit, Mitigation, Vendor Advisory

Source identifier: nvd@nist.gov

30.09.2026Record modifiedCISA ADP

CISA assessment (SSVC): exploitation: proof of concept, automatable: no

New references:

https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv

Show 2 original changes

Individual changes of this event as published by NVD
Type	Action	Before	After
Reference	added	—	https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv
SSVC assessment	added	—	{"id":"CVE-2026-100650","role":"CISA Coordinator","options":[{"exploitation":"poc"},{"automatable":"no"},{"technicalImpact":"partial"}],"version":"2.0.3","timestamp":"2026-09-30T14:49:40.322864Z"}

Source identifier: 134c704f-9b21-4f2e-91b3-4a467353bcc0

26.09.2026ReceivedVulnCheck

CVSS V4.0: AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

CVSS V3.1: AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Weakness type: CWE-400

Description added or changed

New references:

Show 8 original changes

Individual changes of this event as published by NVD
Type	Action	Before	After
Description	added	—	vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.
CVSS	added	—	AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CVSS	added	—	AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Weakness type (CWE)	added	—	CWE-400
Affected versions (publisher)	added	—	New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/100xxx/CVE-2026-100650.json">CVE-2026-100650</a>
Reference	added	—	https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34
Reference	added	—	https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv
Reference	added	—	https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization

Source identifier: disclosure@vulncheck.com

Embed badge

Show the severity and KEV status of this vulnerability on your site – with a link back here. The image is updated hourly.

<a href="https://intel.neosec.eu/en/cve/CVE-2026-100650"><img src="https://intel.neosec.eu/badge/cve/CVE-2026-100650.svg?lang=en" alt="CVE-2026-100650 – NEOSEC Intel" height="20"></a>