CVE-2026-27893: Vllm Remote Code Execution Vulnerability

HIGH
Advisory Identifier: GHSA-7972-pg2x-xr59
CVSS 8.8
CWE-693
Published
Advisory Summary

CVE-2026-27893 is a HIGH (CVSS 8.8) remote code execution vulnerability (CWE-693: Protection Mechanism Failure) affecting Vllm libraries in the PyPI ecosystem. The issue involves vllm has hardcoded trust override in model files enables rce despite explicit user opt-out. Remediation is available by upgrading affected packages to version 0.18.0.

CVE-2026-27893 at a Glance

CVE Identifier CVE-2026-27893
GHSA Identifier GHSA-7972-pg2x-xr59
Severity HIGH
CVSS v3.1 Base Score 8.8
CWE Classification CWE-693: Protection Mechanism Failure
Affected Product Vllm
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 8.8

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required None (PR:N)
User Interaction Required (UI:R)
Scope Unchanged (S:U)
Confidentiality High (C:H)
Integrity High (I:H)
Availability High (A:H)

How to Fix CVE-2026-27893

To remediate this vulnerability, upgrade all affected Vllm dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

vllm fixed: 0.18.0
pip install vllm>=0.18.0
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release:

pip show vllm

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2026-27893, inspect your installed packages using pip:

pip show vllm

Analyze the terminal output to locate any version of Vllm in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 0.18.0), your application is affected.

Note: The pip show vllm command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-693: Protection Mechanism Failure, where the product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product. In Vllm, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

### Summary 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. ### Details **Affected files (latest main branch):** 1. `vllm/model_executor/models/nemotron_vl.py:430` ```python vision_model = AutoModel.from_config(config.vision_config, trust_remote_code=True) ``` 2. vllm/model_executor/models/kimi_k25.py:177 ```python cached_get_image_processor(self.ctx.model_config.model, trust_remote_code=True) ``` Both pass a hardcoded trust_remote_code=True to HuggingFace API calls, overriding the user's global --trust-remote-code=False setting. Relation to prior CVEs: - CVE-2025-66448 fixed auto_map resolution in vllm/transformers_utils/config.py (config loading path) - CVE-2026-22807 fixed broader auto_map at startup - Both fixes are present in the current code. These hardcoded instances in model files survived both patches — different code paths. ### Impact Remote code execution. An attacker can craft a malicious model repository that executes arbitrary Python code when loaded by vLLM, even when the user has explicitly set --trust-remote-code=False. This undermines the security guarantee that trust_remote_code=False is intended to provide. Remediation: Replace hardcoded trust_remote_code=True with self.config.model_config.trust_remote_code in both files. Raise a clear error if the model component requires remote code but the user hasn't opted in.

CVE-2026-27893 Affected Vllm Versions

1 component(s)
Fixed Versions:
0.18.0
Product / Package Ecosystem Affected Versions Fixed Version
vllm
PyPI
≥ 0.10.1
< 0.18.0
0.18.0

References

GitHub Advisory / Wiki ADVISORY
https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
NVD — CVE-2026-27893 NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-27893
Vllm Source Repository REPOSITORY
https://github.com/vllm-project/vllm/pull/36192
Security Fix Commit FIX COMMIT
https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
Vllm Security Information SECURITY
https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json
Vllm Source Repository REPOSITORY
https://github.com/vllm-project/vllm
Vllm Source Repository REPOSITORY
https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2297.yaml
bugzilla.redhat.com/show_bug.cgi WEB
https://bugzilla.redhat.com/show_bug.cgi?id=2452055
Vllm Security Information SECURITY
https://access.redhat.com/security/cve/CVE-2026-27893
access.redhat.com/errata/rhsa-2026:87... WEB
https://access.redhat.com/errata/RHSA-2026:8748
access.redhat.com/errata/rhsa-2026:87... WEB
https://access.redhat.com/errata/RHSA-2026:8747
access.redhat.com/errata/rhsa-2026:87... WEB
https://access.redhat.com/errata/RHSA-2026:8746
access.redhat.com/errata/rhsa-2026:37... WEB
https://access.redhat.com/errata/RHSA-2026:37275
access.redhat.com/errata/rhsa-2026:24... WEB
https://access.redhat.com/errata/RHSA-2026:24977
access.redhat.com/errata/rhsa-2026:19... WEB
https://access.redhat.com/errata/RHSA-2026:19725
access.redhat.com/errata/rhsa-2026:19... WEB
https://access.redhat.com/errata/RHSA-2026:19724
access.redhat.com/errata/rhsa-2026:19... WEB
https://access.redhat.com/errata/RHSA-2026:19712
access.redhat.com/errata/rhsa-2026:10... WEB
https://access.redhat.com/errata/RHSA-2026:10141
access.redhat.com/errata/rhsa-2026:10... WEB
https://access.redhat.com/errata/RHSA-2026:10140

Frequently Asked Questions

What is CVE-2026-27893?
CVE-2026-27893 is a security vulnerability in Vllm involving vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out under CWE-693: Protection Mechanism Failure.
Which Vllm versions are affected?
Affected versions include releases prior to 0.18.0 across affected packages: vllm.
What version fixes CVE-2026-27893?
Upgrading to 0.18.0 (or the latest patched release for your respective branch) resolves the vulnerability.
Is vllm affected?
Yes, vllm is affected in releases prior to 0.18.0. Upgrade your dependency to 0.18.0 or later.
What is the CVSS score of CVE-2026-27893?
CVE-2026-27893 has a CVSS v3.1 base score of 8.8 (HIGH) with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
What CWE is associated with CVE-2026-27893?
CVE-2026-27893 is classified under CWE-693: Protection Mechanism Failure (The product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product.).
How can I check PyPI dependencies for CVE-2026-27893?
Run the dependency tree command: 'pip show vllm'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-7972-pg2x-xr59",
  "modified" : "2026-07-17T16:18:07Z",
  "published" : "2026-03-27T15:27:20Z",
  "aliases" : [ "CVE-2026-27893" ],
  "summary" : "vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out",
  "details" : "### Summary\n\n  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\n  repositories even when the user has explicitly disabled remote code trust.\n\n  ### Details\n\n  **Affected files (latest main branch):**\n\n  1. `vllm/model_executor/models/nemotron_vl.py:430`\n  ```python\n  vision_model = AutoModel.from_config(config.vision_config, trust_remote_code=True)\n```\n\n  2. vllm/model_executor/models/kimi_k25.py:177\n \n```python\n  cached_get_image_processor(self.ctx.model_config.model, trust_remote_code=True)\n```\n\n  Both pass a hardcoded trust_remote_code=True to HuggingFace API calls, overriding the user's global --trust-remote-code=False setting.\n\n  Relation to prior CVEs:\n  - CVE-2025-66448 fixed auto_map resolution in vllm/transformers_utils/config.py (config loading path)\n  - CVE-2026-22807 fixed broader auto_map at startup\n  - Both fixes are present in the current code. These hardcoded instances in model files survived both patches — different code paths.\n\n### Impact\n\n  Remote code execution. An attacker can craft a malicious model repository that executes arbitrary Python code when loaded by vLLM, even when the user has explicitly set --trust-remote-code=False. This undermines the security guarantee\n  that trust_remote_code=False is intended to provide.\n\n  Remediation: Replace hardcoded trust_remote_code=True with self.config.model_config.trust_remote_code in both files. Raise a clear error if the model component requires remote code but the user hasn't opted in.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "vllm"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0.10.1"
      }, {
        "fixed" : "0.18.0"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59"
  }, {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-27893"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/pull/36192"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72"
  }, {
    "type" : "WEB",
    "url" : "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/vllm-project/vllm"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2297.yaml"
  }, {
    "type" : "WEB",
    "url" : "https://bugzilla.redhat.com/show_bug.cgi?id=2452055"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/security/cve/CVE-2026-27893"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:8748"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:8747"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:8746"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:37275"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:24977"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:19725"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:19724"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:19712"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:10141"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:10140"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-693" ],
    "severity" : "HIGH",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-03-27T15:27:20Z",
    "nvd_published_at" : "2026-03-27T00:16:22Z"
  }
}