vLLM affected by RCE via auto_map dynamic module loading during model initialization
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2026-22807
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 3 Nov 2026, 00:55 UTC · Revision 1
Source evidence
vLLM affected by RCE via auto_map dynamic module loading during model initialization
core-osv · Original sourcePublished 21 Jan 2026, 21:13 UTC
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.
osv:CVE-2026-22807
Complete source record
{
"id": "3db80cd0f617fb927390ab0d60cab65f2bf0136a9dfdab5e0fca2ea39e20ace8",
"url": "https://osv.dev/vulnerability/CVE-2026-22807",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "vLLM affected by RCE via auto_map dynamic module loading during model initialization",
"summary": "vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.",
"evidence": "osv:CVE-2026-22807",
"products": [],
"severity": "high",
"structured": {
"id": "CVE-2026-22807",
"aliases": [
"CVE-2026-22807",
"GHSA-2pc9-4j83-qjmr",
"PYSEC-2026-2010"
],
"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": "b17039bccc17b94a2ea107272ad7bc93508708df"
},
{
"fixed": "78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5"
}
],
"database_specific": {
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.10.1"
},
{
"fixed": "0.14.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5"
}
],
"source": "REFERENCES_COMMIT"
},
{
"range": [
{
"fixed": "b17039bccc17b94a2ea107272ad7bc93508708df"
}
],
"source": "REFERENCES_TAG",
"original_tag": "v0.14.0"
}
]
}
}
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-22807.json"
}
}
],
"modified": "2026-10-28T02:30:24.973932166Z",
"provider": "osv",
"references": [
"https://github.com/vllm-project/vllm/releases/tag/v0.14.0",
"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-22807.json",
"https://access.redhat.com/errata/RHSA-2026:10184",
"https://access.redhat.com/errata/RHSA-2026:30087",
"https://access.redhat.com/errata/RHSA-2026:30088",
"https://access.redhat.com/errata/RHSA-2026:30089",
"https://access.redhat.com/errata/RHSA-2026:3461",
"https://access.redhat.com/errata/RHSA-2026:3462",
"https://access.redhat.com/errata/RHSA-2026:3713",
"https://access.redhat.com/errata/RHSA-2026:3782",
"https://access.redhat.com/errata/RHSA-2026:42644",
"https://access.redhat.com/errata/RHSA-2026:5119",
"https://access.redhat.com/security/cve/CVE-2026-22807",
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/22xxx/CVE-2026-22807.json",
"https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr",
"https://nvd.nist.gov/vuln/detail/CVE-2026-22807",
"https://bugzilla.redhat.com/show_bug.cgi?id=2431865",
"https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5",
"https://github.com/vllm-project/vllm/pull/32194"
],
"provider_metadata": {
"cwe_ids": [
"CWE-94"
],
"cna_assigner": "GitHub_M",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/22xxx/CVE-2026-22807.json"
}
},
"related_cves": [
{
"value": "CVE-2026-22807",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 491359,
"published_at": "2026-01-21T21:13:11.894+00:00"
}