CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
Description
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.
INFO
Published Date :
Jan. 21, 2026, 10:15 p.m.
Last Modified :
Jan. 21, 2026, 10:15 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
Affected Products
The following products are affected by CVE-2026-22807
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 3.1 | HIGH | MITRE-CVE |
Solution
- Update vLLM to version 0.14.0 or later.
- Ensure remote code loading is properly gated.
- Review model repository access controls.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-22807.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-22807 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-22807
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-22807 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-22807 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Jan. 21, 2026
Action Type Old Value New Value Added Description 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. Added CVSS V3.1 AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CWE CWE-94 Added Reference https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5 Added Reference https://github.com/vllm-project/vllm/pull/32194 Added Reference https://github.com/vllm-project/vllm/releases/tag/v0.14.0 Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr