LiveActive security incident?Get immediate response
CVE Record

CVE-2026-27893: vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.

HighCVSS 8.8Not KEV-listedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

Affected vLLM releases can execute code supplied by a malicious model repository even when an operator explicitly disables remote-code trust. Successful exploitation could compromise the serving environment’s confidentiality, integrity, and availability. The upstream fix is vLLM 0.18.0.

Executive priority

Prioritize remediation for production or privileged inference systems that accept externally sourced models. Upgrade promptly because the defect defeats an explicit security control and offers potential full compromise, although the supplied evidence does not establish active exploitation.

Technical view

In vLLM 0.10.1 through versions earlier than 0.18.0, the NemotronVL and KimiK25 implementations hardcode trust_remote_code=True for sub-component loading. This overrides --trust-remote-code=False and can permit repository-controlled Python execution when malicious model content is loaded. CVSS 3.1 is 8.8.

Likely exposure

Exposure is most likely where an affected vLLM version loads NemotronVL or KimiK25 content from third-party, user-selected, or otherwise compromiseable model repositories. Installation alone does not establish exploitation. The supplied vector indicates loading the malicious model requires user or workflow interaction.

Exploitation context

The bundle marks this CVE as absent from KEV and provides no evidence of active exploitation. Exploitation nevertheless has low stated complexity once a victim or automated workflow loads a malicious repository through an affected implementation.

Researcher notes

The security boundary failure is the forced trust_remote_code=True value in two model implementations, categorized as CWE-501 and CWE-693. Assessment should focus on the affected code paths, repository provenance, and process privileges. The bundle does not identify public exploitation or a proof of concept.

Mitigation direction

  • Upgrade upstream vLLM to version 0.18.0 or later.
  • Until upgraded, avoid the affected NemotronVL and KimiK25 implementations.
  • Permit model loading only from approved, integrity-verified repositories.
  • Apply least privilege to vLLM processes to limit potential compromise impact.

Validation and detection

  • Inventory vLLM installations and identify versions from 0.10.1 through versions earlier than 0.18.0.
  • Determine whether NemotronVL or KimiK25 models have been loaded on affected systems.
  • Review loaded model repositories and revisions for approved provenance and expected integrity.
  • Confirm remediated installations run vLLM 0.18.0 or later.
  • Investigate model-loading records for unexpected repositories or associated code execution.
Prepared
Confidence
high
Sources
5

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · low confidence lookup

CWE-501: Exact CWE lookup

Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
cwe · low confidence lookup

CWE-693: Exact CWE lookup

Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
description · low confidence lookup

Execution behavior lookup

The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-27893 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
High
CVSS
8.8 (3.1)
Known Exploited
No
Published

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

2CVSS vectors
5Timeline events
2ADP providers
18Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: noTechnical Impact: total

CVSS vector scores

2 official scores

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
8.8CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H2.85.9GitHub_M
8.8CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H2.85.9redhat-SADP

Vulnerability scoring details

Base CVSS 3.1 score

8.8High
CVSS 3.1 vector shape for CVE-2026-27893Attack VectorAttack ComplexityPrivileges RequiredUser InteractionScopeConfidentiality ImpactIntegrity ImpactAvailability Impact

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Privileges Required
NoneLowHigh
User Interaction
NoneRequired
Scope
ChangedUnchanged
Confidentiality Impact
HighLowNone
Integrity Impact
HighLowNone
Availability Impact
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. CVE publishedCVE Program

    The CVE record was published.

  4. ADP timelineredhat-SADP

    Reported to Red Hat.

  5. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvc
redhat-SADPvllm: vLLM: Remote code execution due to hardcoded trust_remote_code setting
other:Red Hat severity ratingcvssV3_1
  • 2026-03-27T00:01:43.935Z: Reported to Red Hat.
  • 2026-03-26T23:56:53.579Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
vllm-projectvllm>= 0.10.1, < 0.18.0Listed
Weakness

CWE details

CWE-501CWE-693

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.

CWE-501 · source CWE mapping

Trust Boundary Violation

Trust Boundary Violation represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs
CWE-693 · source CWE mapping

Protection Mechanism Failure

Protection Mechanism Failure represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs