CVE-2025-66448 Vulnerability Analysis & Exploit Details

CVE-2025-66448 Vulnerability Summary

CVE-2025-66448: 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.

CVE-2025-66448 References

External References

• https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86
• https://github.com/vllm-project/vllm/pull/28126
• https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm

CWE Common Weakness Enumeration

CAPEC Common Attack Pattern Enumeration and Classification

• Code Injection CAPEC-242 An adversary exploits a weakness in input validation on the target to inject new code into that which is currently executing. This differs from code inclusion in that code inclusion involves the addition or replacement of a reference to a code file, which is subsequently loaded by the target and used as part of the code of some application.
• Leverage Executable Code in Non-Executable Files CAPEC-35 An attack of this type exploits a system's trust in configuration and resource files. When the executable loads the resource (such as an image file or configuration file) the attacker has modified the file to either execute malicious code directly or manipulate the target process (e.g. application server) to execute based on the malicious configuration parameters. Since systems are increasingly interrelated mashing up resources from local and remote sources the possibility of this attack occurring is high.
• Manipulating User-Controlled Variables CAPEC-77 This attack targets user controlled variables (DEBUG=1, PHP Globals, and So Forth). An adversary can override variables leveraging user-supplied, untrusted query variables directly used on the application server without any data sanitization. In extreme cases, the adversary can change variables controlling the business logic of the application. For instance, in languages like PHP, a number of poorly set default configurations may allow the user to override variables.

Other 5 Recently Published CVEs Vulnerabilities

• CVE-2025-66448 – 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 co...
• CVE-2025-66415 – fastify-reply-from is a Fastify plugin to forward the current HTTP request to another server. Prior to 12.5.0, by crafting a malicious URL, an atta...
• CVE-2025-66412 – Angular is a development platform for building mobile and desktop web applications using TypeScript/JavaScript and other languages. Prior to 21.0.2...
• CVE-2025-66410 – Gin-vue-admin is a backstage management system based on vue and gin. In 2.8.6 and earlier, attackers can delete any file on the server at will, cau...
• CVE-2025-66405 – Portkey.ai Gateway is a blazing fast AI Gateway with integrated guardrails. Prior to 1.14.0, the gateway determined the destination baseURL by prio...