vLLM up to 0.11.0 get_class_from_dynamic_module code injection

Summaryinfo

A vulnerability was found in vLLM up to 0.11.0. It has been classified as critical. Affected by this issue is the function get_class_from_dynamic_module. This manipulation causes code injection. This vulnerability is handled as CVE-2025-66448. The attack can be initiated remotely. There is not any exploit available. Upgrading the affected component is recommended.

Detailsinfo

A vulnerability was found in vLLM up to 0.11.0. It has been declared as critical. Affected by this vulnerability is the function get_class_from_dynamic_module. 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. The summary by CVE is:

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.

The advisory is shared at github.com. This vulnerability is known as CVE-2025-66448 since 12/01/2025. The exploitation appears to be difficult. The attack can be launched remotely. Technical details are known, but no exploit is available. MITRE ATT&CK project uses the attack technique T1059 for this issue.

Upgrading to version 0.11.1 eliminates this vulnerability. Applying the patch ffb08379d8870a1a81ba82b72797f196838d0c86 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.

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

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

License

• open-source

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion