Skip to content
Heist/ feed
Back to feed
High

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

Type: advisorySources: OSV

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.

Products
Not specified
Affected versions
Not specified
Fixed versions
Not specified
CVEs
CVE-2026-27893
Confirmed fixed CVEs
Not specified
Updated in this feed
8 Nov 2026, 03:11 UTC · Revision 1

Source evidence

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

core-osv · Original source

Published 26 Mar 2026, 23:56 UTC

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.

osv:CVE-2026-27893
Complete source record
{
  "id": "0026febbfeb13f25e1ec59be507018b6b58117500fb4359a29de4fb5fe6f2870",
  "url": "https://osv.dev/vulnerability/CVE-2026-27893",
  "method": "structured",
  "payload": {
    "kind": "advisory",
    "title": "vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out",
    "summary": "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.",
    "evidence": "osv:CVE-2026-27893",
    "products": [],
    "severity": "high",
    "structured": {
      "id": "CVE-2026-27893",
      "aliases": [
        "CVE-2026-27893",
        "GHSA-7972-pg2x-xr59",
        "PYSEC-2026-2297"
      ],
      "metrics": [
        {
          "type": "CVSS_V3",
          "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H"
        }
      ],
      "affected": [
        {
          "ranges": [
            {
              "repo": "https://github.com/vllm-project/vllm",
              "type": "GIT",
              "events": [
                {
                  "introduced": "aab549870df50edf0512f0a59b574f692f546465"
                },
                {
                  "fixed": "bcf2be96120005e9aea171927f85055a6a5c0cf6"
                },
                {
                  "fixed": "00bd08edeee5dd4d4c13277c0114a464011acf72"
                }
              ],
              "database_specific": {
                "extracted_events": [
                  {
                    "cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                    "range": [
                      {
                        "introduced": "0.10.1"
                      },
                      {
                        "fixed": "0.18.0"
                      }
                    ],
                    "source": "CPE_RANGE"
                  },
                  {
                    "range": [
                      {
                        "fixed": "00bd08edeee5dd4d4c13277c0114a464011acf72"
                      }
                    ],
                    "source": "REFERENCES_COMMIT"
                  }
                ]
              }
            }
          ],
          "database_specific": {
            "source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-27893.json"
          }
        }
      ],
      "modified": "2026-10-28T02:30:53.413582120Z",
      "provider": "osv",
      "references": [
        "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json",
        "https://access.redhat.com/errata/RHSA-2026:10140",
        "https://access.redhat.com/errata/RHSA-2026:10141",
        "https://access.redhat.com/errata/RHSA-2026:19712",
        "https://access.redhat.com/errata/RHSA-2026:19724",
        "https://access.redhat.com/errata/RHSA-2026:19725",
        "https://access.redhat.com/errata/RHSA-2026:24977",
        "https://access.redhat.com/errata/RHSA-2026:37275",
        "https://access.redhat.com/errata/RHSA-2026:42644",
        "https://access.redhat.com/errata/RHSA-2026:8746",
        "https://access.redhat.com/errata/RHSA-2026:8747",
        "https://access.redhat.com/errata/RHSA-2026:8748",
        "https://access.redhat.com/security/cve/CVE-2026-27893",
        "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/27xxx/CVE-2026-27893.json",
        "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59",
        "https://nvd.nist.gov/vuln/detail/CVE-2026-27893",
        "https://bugzilla.redhat.com/show_bug.cgi?id=2452055",
        "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72",
        "https://github.com/vllm-project/vllm/pull/36192"
      ],
      "provider_metadata": {
        "cwe_ids": [
          "CWE-693"
        ],
        "cna_assigner": "GitHub_M",
        "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/27xxx/CVE-2026-27893.json"
      }
    },
    "related_cves": [
      {
        "value": "CVE-2026-27893",
        "evidence": "/id"
      }
    ],
    "security_relevant": true,
    "severity_evidence": "/severity/0/score"
  },
  "source_id": "core-osv",
  "document_id": 522096,
  "published_at": "2026-03-26T23:56:53.579+00:00"
}