vLLM 缓冲区错误漏洞

vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. A buffer error vulnerability exists in vLLM versions 0.10.2 through prior to 0.11.1, which stems from the presence of a memory corruption in the Completions API endpoint that could lead to a cras...

CVE-2025-62426: Allocation of Resources Without Limits or Throttling

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the...

CVE-2025-62164: Improper Input Validation

vLLM is an inference and serving engine for large language models LLMs. From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash denial-of-service and potentially remote code execution RCE, exists in the Completions API endpoint. When processing user-supplied...

vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

Summary The /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chattemplatekwargs parameters, it is possible to block processing of the API server for long...

GHSA-69J4-GRXJ-J64P vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

Summary The /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chattemplatekwargs parameters, it is possible to block processing of the API server for long...

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the applyhfchattemplate method. An authenticated user can cause the server to become...

vLLM deserialization vulnerability leading to DoS and potential RCE

Summary A memory corruption vulnerability that leading to a crash denial-of-service and potentially remote code execution RCE exists in vLLM versions 0.10.2 and later, in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using...

Out-of-bounds Write

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Out-of-bounds Write via the todense function in the Completions API endpoint when processing user-supplied prompt embeddings. An attacker can achiev...

GHSA-MRW7-HF4F-83PF vLLM deserialization vulnerability leading to DoS and potential RCE

Summary A memory corruption vulnerability that leading to a crash denial-of-service and potentially remote code execution RCE exists in vLLM versions 0.10.2 and later, in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using...

The vulnerability in the AuthenticationMiddleware class of the vLLM library allows attackers to bypass security restrictions and disclose sensitive information.

The vulnerability of the AuthenticationMiddleware class in the library for working with Large Language Models LLMs like vLLM is related to the use of hidden time channels for data transmission. Exploiting this vulnerability can allow an attacker to bypass security restrictions and disclose...

CVE-2025-6242 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

CVE-2025-59425 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

CVE-2025-61620 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

GHSA-3F6C-7FW2-PPM4 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

GHSA-6FVQ-23CW-5628 vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

GHSA-WR9H-G72X-MWHM vulnerabilities

Vulnerabilities for packages: py3-vllm-cuda-12.4, tritonserver-backend-vllm-cuda-12.9...

Server-side Request Forgery (SSRF)

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the loadfromurl and loadfromurlasync methods of the MediaConnector class, which fetch and process media from...

GHSA-3F6C-7FW2-PPM4 vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class

Summary A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows...

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling through the chattemplate and chattemplatekwargs parameters. An attacker can cause excessive CPU...

GHSA-6FVQ-23CW-5628 vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server

Summary A resource-exhaustion denial-of-service vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the chattemplate and chattemplatekwargs parameters. If an attacker can supply these parameters to the API, they can cause a...