BlackTreeIndependent security intelligence
← Back to the CVE catalogue
Full vulnerability report · 2026
CVE-2026-7141High confidence

vLLM KV Block kv_cache_interface.py has_mamba_layers uninitialized resource

n/a · vLLM

6.3MediumCVSS 4.0
Recommended action
Within 7 days

Medium technical severity with public exploit material referenced by a structured source; prioritise exposed affected systems while verifying vendor guidance.

Mitigation available
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-2026-7141 · CSAF 2.0 · revision 3 · finalRed Hat Product Securityvllm: vllm: Uninitialized resource in KV Block Handler via has_mamba_layers function
19 known affected

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

  • rhaiis/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server
  • rhaiis/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server
  • rhaiis/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server
  • rhaiis/vllm-rocm-rhel9 as a component of Red Hat AI Inference Server
  • 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
  • rhelai3/bootc-aws-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
  • rhelai3/bootc-azure-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
  • rhelai3/bootc-azure-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
  • rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
  • rhelai3/bootc-gcp-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
  • rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
Summary
A flaw was found in vllm. A remote attacker can exploit a vulnerability in the `has_mamba_layers` function within the KV Block Handler component. By performing a specific manipulation, an uninitialized resource can be triggered, potentially leading to information disclosure or denial of service. The attack is considered to have high complexity, and exploitation is difficult.
Remediation
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Optional official sources

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

Select the national-authority views to include. The exact source language is shown on each matched advisory. Your choice is remembered on this device and encoded in the shareable URL.

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-2026-25892

No EUVD known-exploited evidence

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."

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
6.3 · CVSS 4.0
Advisory evidence
No linked advisory details stored yet
Recommended actionWithin 7 days

Medium technical severity with public exploit material referenced by a structured source; prioritise exposed affected systems while verifying vendor guidance.

Mitigation available
01

What, why and how

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."

What

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."

Why

The product uses or accesses a resource that has not been initialized.

How

An attacker operating through a network path may attempt exploitation without authentication or user interaction. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

What

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."

Why

The product uses or accesses a resource that has not been initialized.

How

An attacker operating through a network path may attempt exploitation without authentication or user interaction. 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.
Reference recorded

CISA Vulnrichment records proof-of-concept exploitation in its SSVC data. BlackTree has not independently executed or validated exploit material.

Likely attack path
a network path → Use of Uninitialized Resource → cause the confidentiality, integrity or availability impact described by the vendor
Attack surface
Network
Privileges required
None: unauthenticated exploitation is possible
User interaction
None
Attack complexity
High: exploitation depends on specific conditions
Security boundary
Not a CVSS 4.0 base metric
Weakness
?CWE means Common Weakness Enumeration: a standard category for the underlying weakness.
CWE-908 ↗

CWE-908: Use of Uninitialized Resource. The product uses or accesses a resource that has not been initialized.

CVSS vector
?CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity.
CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P

Common Vulnerability Scoring System 4.0: the compact vector below is decoded into plain language.

AVNetworkAttack vector: The vulnerable component can be reached over a network.ACHighAttack complexity: Successful exploitation depends on specific conditions outside the attacker's direct control.ATNoneAttack requirements: No additional deployment or execution condition is required.PRNonePrivileges required: The attacker does not need an account or existing privileges.UINoneUser interaction: No action by another user is required.VCLowVulnerable-system confidentiality: A successful attack can cause a limited loss.VILowVulnerable-system integrity: A successful attack can cause a limited loss.VALowVulnerable-system availability: A successful attack can cause a limited loss.SCNoneSubsequent-system confidentiality: No direct loss is represented by this metric.SINoneSubsequent-system integrity: No direct loss is represented by this metric.SANoneSubsequent-system availability: No direct loss is represented by this metric.
Post-exploitation / living off the land
No specific living-off-the-land technique is confirmed in the structured sources. Monitor normal administration tools for activity inconsistent with the affected service's baseline.
NetworkUnauthenticatedCWE-908Public exploit reference
A

Official authority intelligence

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

ENISA EUVD · EUVD-2026-25892Official EUVD mapping

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."

Official EUVD record
BSI · German · WID-SEC-W-2026-1289vllm (KV Block Handler): Schwachstellen ermöglicht Manipulation von Dateien

Ein entfernter, anonymer Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Daten zu manipulieren und nicht näher spezifizierte Angriffe durchzuführen, wodurch vertrauliche Informationen offengelegt werden oder ein Denial-of-Service-Zustand entstehen können.

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.
Mitigation available
Affected
rhaiis/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server; rhaiis/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server; rhaiis/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server; rhaiis/vllm-rocm-rhel9 as a component of Red Hat AI Inference Server; 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; rhelai3/bootc-aws-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-azure-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-azure-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-gcp-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3; rhoai/odh-kserve-agent-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-controller-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-router-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-kserve-storage-initializer-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-cuda-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-gaudi-rhel9 as a component of Red Hat OpenShift AI (RHOAI); rhoai/odh-vllm-rocm-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
Fixed
No fixed version is explicitly recorded in the structured CVE data.
Action
No verified patch reference is present in the current structured sources. Check the vendor advisory before making a change.
Workaround
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
04

Evidence and provenance

Published 27 Apr 2026 · Last source change 25 Aug 2026, 19:07 UTC · CWE-908 · Use of Uninitialized Resource

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-2026-25892
Product sourceVendor CSAF · Red Hat Product Security
Remediation sourceVendor CSAF · Red Hat Product Security
CWE sourceCNA
NVD statusNVD modified after enrichment

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

Material change intelligence

What changed after publication

View recent updates →
  1. Vendor guidanceAuthoritative vendor guidance changed from authoritative remediation link · patch to no authoritative guidance recorded.
    Before
    authoritative remediation link · patch
    After
    no authoritative guidance recorded
    CNA ↗
  2. Affected versionsThe structured affected or fixed version information changed.
    Before
    0.1; 0.2; 0.3; 0.4; 0.5; 0.6; 0.7; 0.8 · 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
    0.1; 0.2; 0.3; 0.4; 0.5; 0.6; 0.7; 0.8 · Fixed: No fixed version is explicitly recorded in the structured CVE data.
    CNA ↗
  3. Remediation statusRemediation status changed from Patch available to Awaiting fix.
    Before
    Patch available
    After
    Awaiting fix
    CNA ↗
  4. Vendor guidanceAuthoritative vendor guidance changed from authoritative remediation link · patch to authoritative remediation link · patch.
    Before
    authoritative remediation link · patch
    After
    authoritative remediation link · patch
    cna@vuldb.com ↗
Material fields only · duplicate refreshes suppressed · history retained for the configured operational retention period
CVE published
ENISA EUVD · EUVD-2026-25892↗Vendor CSAF · Red Hat Product Security↗CISA Vulnrichment SSVC evidence↗CVE authority or vendor 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-2026-7141 · cve.blacktree.nl