← Back to CVEs
CVE-2026-22807
HIGH8.8
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.
CVE Details
CVSS v3.1 Score8.8
SeverityHIGH
CVSS VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack VectorNETWORK
ComplexityLOW
Privileges RequiredNONE
User InteractionREQUIRED
Published1/21/2026
Last Modified1/30/2026
Sourcenvd
Honeypot Sightings0
Affected Products
vllm:vllm
Weaknesses (CWE)
CWE-94
References
https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5(security-advisories@github.com)
https://github.com/vllm-project/vllm/pull/32194(security-advisories@github.com)
https://github.com/vllm-project/vllm/releases/tag/v0.14.0(security-advisories@github.com)
https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr(security-advisories@github.com)
IOC Correlations
No correlations recorded
This product uses data from the NVD API but is not endorsed or certified by the NVD.