BlackTreeCVE Intelligence
← Back to the CVE catalogue
Full vulnerability report · 2025
CVE-2025-62426High confidence

vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

vllm-project · vllm

Official source article: GitHub GHSA-69J4-GRXJ-J64P ↗. Check the applicable product and release in the original source.

6.5MediumCVSS 3.1
Recommended action
Scheduled

Medium technical severity with no CISA KEV confirmation; remediate through the normal risk-based patch cycle unless local exposure raises the priority.

Patch available
R
Operational reassessment

Published severity in operational context

Open reassessment dashboard →
Published severityMediumOperational priority:Medium, unchanged from published severity.unchanged

Evidence used

  • No CISA KEV confirmation is currently recorded.
  • EPSS is 0.37% for the current model date.

Compensating controls

  • Validate the affected product branch and deploy the verified fixed release.
  • Restrict the affected network interface to trusted sources where business-safe.
  • Monitor vendor guidance and exploitation sources for a material change.

Verification

  1. Confirm that the asset runs vllm-project vllm and falls inside the recorded affected range.
  2. Verify the installed build against the product-specific fixed version after deployment.
  3. Validate exposure, authentication requirements and compensating controls in the actual environment.
  4. Reopen this reassessment when CVSS, KEV, EPSS, exploit evidence or remediation changes.
Mitigation target: As exposure requiresRemediation target: Within 365 days

This automated reassessment organises public evidence. It does not know asset exposure, business impact or control effectiveness and does not replace CVSS or a human risk decision.

Open-source package ranges2 source-attributed ranges

These OSV and GitHub advisory ranges apply only to the named package and ecosystem. A listed fixed version is not a universal product patch or proof that an update is installed.

Ecosystem and packageAffected rangeFirst fixed versionEvidence
PyPIvllmECOSYSTEM: introduced 0.5.5; fixed 0.11.10.11.1OSV record ↗aggregator derived · 10 Sep 2026
pipvllm>= 0.5.5, < 0.11.10.11.1GitHub advisory ↗upstream repository advisory · 17 Jul 2026
Direct vendor intelligence

Authoritative vendor CSAF and VEX advisories

Structured product status and remediation from the issuing vendor. Product-state explanations are always visible; large lists can be searched or downloaded.

1 current
CVE-2025-62426 · CSAF 2.0 · revision 3 · finalRed Hat Product Securityvllm: vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
24 known affected

The vendor explicitly identifies these products as affected by this CVE.

  • rhaiis/vllm-spyre-rhel9 as a component of Red Hat AI Inference Server
  • rhaiis/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server
  • rhelai1/bootc-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/bootc-aws-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/bootc-azure-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/bootc-azure-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/bootc-gcp-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/bootc-intel-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/bootc-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/instructlab-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/instructlab-intel-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
  • rhelai1/instructlab-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
Summary
A vulnerability in vLLM allows an authenticated user to trigger unintended tokenization during chat template processing by supplying crafted chat_template_kwargs to the /v1/chat/completions or /tokenize endpoints. By forcing the server to tokenize very large inputs, an attacker can block the API server’s event loop for extended periods, causing a denial of service and delaying all other requests.
Remediation
For more information visit https://access.redhat.com/errata/RHSA-2026:3461
Optional official sources

National CERT insights
?CERT means Computer Emergency Response Team; CSIRT is the closely related term Computer Security Incident Response Team.

Choose official national sources for this report. Each advisory shows its original language. Your selection is remembered on this device and included in shared links.

Official European source

ENISA European Vulnerability Database

Official EUVD identifiers, advisory evidence and known-exploited context. Missing fields are not treated as evidence of low risk.

1 current
ENISA EUVD identifier

EUVD-2025-198356

No EUVD known-exploited evidence

ENISA has published the identifier mapping but no EUVD description has been stored yet.

EUVD state
Present in the current official mapping
Known exploitation
Not present in the current ENISA EUVD known-exploited dataset. This is not proof of no exploitation.
ENISA score
Not supplied in the stored EUVD record
Advisory evidence
No linked advisory details stored yet
Recommended actionScheduled

Medium technical severity with no CISA KEV confirmation; remediate through the normal risk-based patch cycle unless local exposure raises the priority.

Patch available
01

What, why and how

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

What

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

Why

The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.

How

An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

What

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

Why

The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.

How

An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

02

Exploit reality and attack path

CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.

Observed exploitation
?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.
No confirmed evidence

No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.

Public PoC / exploit material
?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.
None recorded

No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.

Likely attack path
a network path → Allocation of Resources Without Limits or Throttling → cause the confidentiality, integrity or availability impact described by the vendor
Attack surface
Network
Privileges required
Low: a basic authenticated account is required
User interaction
None
Attack complexity
Low: no specialised conditions are recorded
Security boundary
Unchanged: impact remains within the vulnerable component's security authority
Weakness
?CWE means Common Weakness Enumeration: a standard category for the underlying weakness.
CWE-770 ↗

CWE-770: Allocation of Resources Without Limits or Throttling. The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.

CVSS vector
?CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Common Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.

AVNetworkAttack vector: The vulnerable component can be reached over a network.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.PRLowPrivileges required: The attacker needs basic user-level privileges.UINoneUser interaction: No action by another user is required.SUnchangedScope: The security impact remains within the vulnerable component's authority.CNoneConfidentiality impact: No direct loss is represented by this metric.INoneIntegrity impact: No direct loss is represented by this metric.AHighAvailability impact: A successful attack can cause a major loss.
Post-exploitation / living off the land
Stolen credentials, tokens and legitimate administration functions may provide continued access without deploying a large custom toolset.
NetworkCWE-770
A

Official authority intelligence

Only matched European and national findings are included. Language selectors and unavailable sources are omitted.

Cyber Security Agency of Singapore · English · CSA-SB-20251126Security Bulletin 26 Nov 2025

The Cyber Security Agency of Singapore included this CVE in its official Security Bulletin 26 Nov 2025, published on 26 November 2025. Open the linked bulletin for the product, severity and reference information published in that issue.

Official advisory ↗
CERT-FR · French · CERTFR-2025-AVI-1138Multiples vulnérabilités dans VMware Tanzu Platform

d?id=CVE-2025-58188 Référence CVE CVE-2025-58189 https://www.cve.org/CVERecord?id=CVE-2025-58189 Référence CVE CVE-2025-61723 https://www.cve.org/CVERecord?id=CVE-2025-61723 Référence CVE CVE-2025-61724 https://www.cve.org/CVERecord?id=CVE-2025-61724 Référence CVE CVE-2025-61725 https://www.cve.org/CVERecord?id=CVE-2025-61725 Référence CVE CVE-2025-61727 https://www.cve.org/CVERecord?id=CVE-2025-61727 Référence CVE CVE-2025-61729 https://www.cve.org/CVERecord?id=CVE-2025-61729 Référence CVE CVE-2025-62164 https://www.cve.org/CVERecord?id=CVE-2025-62164 Référence CVE CVE-2025-62372 https://www.cve.org/CVERecord?id=CVE-2025-62372 Référence CVE CVE-2025-62426 https://www.cve.org/CVERecord?id=CVE-2025-62426 Référence CVE CVE-2025-62593 https://www.cve.org/CVERecord?id=CVE-2025-62593 Référence CVE CVE-2025-62727 https://www.cve.org/CVERecord?id=CVE-2025-62727 Référence CVE CVE-2025-66448 https://www.cve.org/CVERecord?id=CVE-2025-66448 Gestion détaillée du document le 26 décembre 2025 Version initiale Alertes Avis Bulletins d’actualités Mentions légales Conditions générales À propos Contact cyber.gouv.fr service-public.fr legifrance.gouv.fr info.gouv.fr france.fr info.gouv.fr/risques Premier Ministre / Secrétariat Général de la Défense et de la Sécurité Nationale / Agence nationale de la sécurité de

Official advisory ↗
CERT-FR · French · CERTFR-2025-AVI-1057Multiples vulnérabilités dans les produits VMware

CVERecord?id=CVE-2025-58056 Référence CVE CVE-2025-58057 https://www.cve.org/CVERecord?id=CVE-2025-58057 Référence CVE CVE-2025-59375 https://www.cve.org/CVERecord?id=CVE-2025-59375 Référence CVE CVE-2025-59425 https://www.cve.org/CVERecord?id=CVE-2025-59425 Référence CVE CVE-2025-6021 https://www.cve.org/CVERecord?id=CVE-2025-6021 Référence CVE CVE-2025-6069 https://www.cve.org/CVERecord?id=CVE-2025-6069 Référence CVE CVE-2025-6141 https://www.cve.org/CVERecord?id=CVE-2025-6141 Référence CVE CVE-2025-6170 https://www.cve.org/CVERecord?id=CVE-2025-6170 Référence CVE CVE-2025-62372 https://www.cve.org/CVERecord?id=CVE-2025-62372 Référence CVE CVE-2025-62426 https://www.cve.org/CVERecord?id=CVE-2025-62426 Référence CVE CVE-2025-65106 https://www.cve.org/CVERecord?id=CVE-2025-65106 Référence CVE CVE-2025-6965 https://www.cve.org/CVERecord?id=CVE-2025-6965 Référence CVE CVE-2025-7709 https://www.cve.org/CVERecord?id=CVE-2025-7709 Référence CVE CVE-2025-8194 https://www.cve.org/CVERecord?id=CVE-2025-8194 Référence CVE CVE-2025-8732 https://www.cve.org/CVERecord?id=CVE-2025-8732 Référence CVE CVE-2025-9086 https://www.cve.org/CVERecord?id=CVE-2025-9086 Référence CVE CVE-2025-9230 https://www.cve.org/CVERecord?id=CVE-2025-9230 Référence CVE CVE-2025-9231 https://www.cve.org/CVERecord?id=CVE-2025-9231

Official advisory ↗
JVN iPedia · Japanese · JVNDB-2025-021229vLLM における制限またはスロットリング無しのリソースの割り当てに関する脆弱性

vLLM には、制限またはスロットリング無しのリソースの割り当てに関する脆弱性が存在します。

Official advisory ↗
03

Patch and workaround

Operational remediation based on structured source evidence.

Status
?Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change.
Patch available
Affected
Fixed
Action
For more information visit https://access.redhat.com/errata/RHSA-2026:3461
Workaround
No verified workaround is recorded. If business-safe, reduce exposure to the affected interface and allow only trusted sources until authoritative guidance is available.
04

Evidence and provenance

Published 21 Nov 2025 · Last source change 24 Nov 2025, 18:12 UTC · CWE-770 · Allocation of Resources Without Limits or Throttling

CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source
?The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.
FIRST · tracked since 2026-08-14
European sourceENISA EUVD · EUVD-2025-198356
Product sourceVendor CSAF · Red Hat Product Security
Remediation sourceVendor CSAF · Red Hat Product Security
CWE sourceCNA
NVD statusNVD enriched

Core structured fields are present and their contributing authorities are shown above.

Material change intelligence

What changed after publication

View recent updates ↗
  1. Affected versionsThe structured affected or fixed version information changed.
    Before
    >= 0.5.5, < 0.11.1 · Fixed: An authoritative update reference is available, but the fixed version is not recorded in the structured CVE fields. Check the linked vendor advisory for the applicable release.
    After
    >= 0.5.5, < 0.11.1 · Fixed: For more information visit https://access.redhat.com/errata/RHSA-2026:3461
    Red Hat Product Security ↗
Material fields only · duplicate refreshes suppressed · history retained for the configured operational retention period
CVE published
Fixed release or patch reference recorded
Fixed release recorded from official guidance
ENISA EUVD · EUVD-2025-198356↗Red Hat Product Security security advisory↗CVE authority or vendor reference · GitHub GHSA-69J4-GRXJ-J64P↗Patch or update reference↗Official CVE record (CNA and ADP data)↗NVD record↗
Technical terms and abbreviations used in this report
CVE
Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
CVSS
Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
EPSS
Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
CWE
Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
CNA
CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
CISA ADP
Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
NVD
National Vulnerability Database: NIST's enrichment service for CVE records.
CERT / CSIRT
A computer security incident response team that publishes warnings or coordinates incident response.
PoC
Proof of concept: public material that demonstrates or helps reproduce exploitation.
CSAF
Common Security Advisory Framework: a machine-readable format for security advisories.
LoTL
Living off the land: abuse of legitimate tools or system functions during an attack.
Free version - for non-commercial use only.CVE-2025-62426 · cve.blacktree.nl