CVE-2026-22807
CRITICAL EPSS 41.4%
Published Jan 21, 20265mo ago · Modified Jun 17, 20261w ago
9.8 CVSS 3.1
Published Jan 21, 2026 5mo ago
Last Modified Jun 17, 2026 1w ago
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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality High
Integrity High
Availability High
Threat Intelligence
EPSS Exploit Probability
41.4% percentile
Exploit & Patch Status
No Known Exploit
Patch Available
Weaknesses 1
CWE-94 Improper Control of Generation of Code (Code Injection) Injection
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| vllm | vllm | * | ≥0.10.1 – <0.14.0 |
References 4
- github.com https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5
- github.com https://github.com/vllm-project/vllm/pull/32194
- github.com https://github.com/vllm-project/vllm/releases/tag/v0.14.0
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr
Remediation
- github.com https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5
- github.com https://github.com/vllm-project/vllm/pull/32194
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr