vLLM up to 0.13.x Hugging Face auto_map code injection

Summaryinfo

A vulnerability labeled as critical has been found in vLLM up to 0.13.x. Impacted is the function auto_map of the component Hugging Face. Executing a manipulation can lead to code injection. This vulnerability is handled as CVE-2026-22807. The attack can be executed remotely. There is not any exploit available. The affected component should be upgraded.

Detailsinfo

A vulnerability classified as critical was found in vLLM up to 0.13.x. This vulnerability affects the function auto_map of the component Hugging Face. The manipulation with an unknown input leads to a code injection vulnerability. The CWE definition for the vulnerability is CWE-94. The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment. As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is available at github.com. This vulnerability was named CVE-2026-22807 since 01/09/2026. The exploitation appears to be easy. The attack can be initiated remotely. No form of authentication is required for a successful exploitation. Successful exploitation requires user interaction by the victim. Technical details are known, but there is no available exploit. This vulnerability is assigned to T1059 by the MITRE ATT&CK project.

Upgrading to version 0.14.0 eliminates this vulnerability. The upgrade is hosted for download at github.com. Applying the patch 78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5 is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

The vulnerability is also documented in the databases at EUVD (EUVD-2026-3678) and CERT Bund (WID-SEC-2026-0190). If you want to get best quality of vulnerability data, you may have to visit VulDB.

Affected

• Open Source vllm

Productinfo

Name

• vLLM

Version

• 0.1
• 0.2
• 0.3
• 0.4
• 0.5
• 0.6
• 0.7
• 0.8
• 0.9
• 0.10
• 0.11
• 0.12
• 0.13

License

• open-source

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion