CVE-2024-11041: Deserialization of Untrusted Data

vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload to the MessageQueue,...

PT-2025-12093

Name of the Vulnerable Software and Affected Versions vllm-project vllm version v0.6.2 Description The issue is related to a remote code execution vulnerability in the MessageQueue.dequeue API function. This function uses pickle.loads to parse received sockets directly, allowing an attacker to...

编号撤回

vLLM is vLLM open source a high throughput and memory efficient inference and service engine for LLM. This CVE number has been withdrawn...

vLLM 代码问题漏洞

vLLM is a vLLM open source high throughput and memory efficient reasoning and serving engine for LLM. A code issue vulnerability exists in vLLM version v0.6.2, which stems from a remote code execution vulnerability in the MessageQueue.dequeue API function...

PT-2025-12092

Name of the Vulnerable Software and Affected Versions vllm versions 0.5.2.2 Description The issue is related to Denial of Service attacks. It occurs in the "POST /v1/completions" and "POST /v1/embeddings" endpoints. For "POST /v1/completions", enabling use beam search and setting best of to a hig...

编号撤回

vLLM is vLLM open source a high throughput and memory efficient inference and service engine for LLM. This CVE number has been withdrawn...

vLLM 操作系统命令注入漏洞

vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. An operating system command injection vulnerability exists in vLLM version 0.6.0, which stems from a failure to clean up deserialized data in the AsyncEngineRPCServer function, which could lead t...

CVE-2025-29770

A flaw was found in vLLM. This vulnerability can allow Denial of Service via filesystem exhaustion. Mitigation Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicabilit...

PYSEC-2025-63

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

CVE-2025-29783

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

PYSEC-2025-223

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output a.k.a. guided decoding. Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has...

CVE-2025-29770

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output a.k.a. guided decoding. Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has...

Deserialization of Untrusted Data

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the MooncakePipe class, which relies on pickle for serialization and deserialization in recvtensor. An attacker...

vLLM Allows Remote Code Execution via Mooncake Integration

Summary When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP will allow attackers to execute remote code on distributed hosts. Details 1. Pickle deserialization vulnerabilities are well documented. 2. The mooncake pipe is exposed over the network by design...

GHSA-X3M8-F7G5-QHM7 vLLM Allows Remote Code Execution via Mooncake Integration

Summary When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP will allow attackers to execute remote code on distributed hosts. Details 1. Pickle deserialization vulnerabilities are well documented. 2. The mooncake pipe is exposed over the network by design...

GHSA-MGRM-FGJV-MHV8 vLLM denial of service via outlines unbounded cache on disk

Impact The outlines library is one of the backends used by vLLM to support structured output a.k.a. guided decoding. Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the...

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 in outlineslogitsprocessors.py module, which uses a local cache with unbounded size by default...

vLLM denial of service via outlines unbounded cache on disk

Impact The outlines library is one of the backends used by vLLM to support structured output a.k.a. guided decoding. Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the...

CVE-2025-29783 vLLM Allows Remote Code Execution via Mooncake Integration

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

CVE-2025-29783 vLLM Allows Remote Code Execution via Mooncake Integration

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...