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-2025-29770 vLLM denial of service via outlines unbounded cache on disk

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 denial of service via outlines unbounded cache on disk

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 denial of service via outlines unbounded cache on disk

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...

PT-2025-11696 · Vllm · Vllm

Name of the Vulnerable Software and Affected Versions: vLLM versions prior to 0.8.0 Description: The issue is related to the outlines library used by vLLM for structured output, which has an optional cache for compiled grammars on the local filesystem. This cache is enabled by default. A maliciou...

PT-2025-18216

Name of the Vulnerable Software and Affected Versions vLLM versions 0.6.5 through 0.8.4 Description vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The issue concerns the use of pickle-based serialization over unsecured ZeroMQ sockets when vLLM is integrated...

vLLM 代码问题漏洞

vLLM is a high throughput and memory efficient inference and service engine for LLM from the vLLM open source. A code issue vulnerability exists in vLLM that stems from insecure deserialization in the Mooncake configuration that could lead to remote code execution...

CVE-2025-1953

A vulnerability has been found in vLLM AIBrix 0.2.0 and classified as problematic. Affected by this vulnerability is an unknown functionality of the file pkg/plugins/gateway/prefixcacheindexer/hash.go of the component Prefix Caching. The manipulation leads to insufficiently random values. The...

CVE-2025-1953

A vulnerability has been found in vLLM AIBrix 0.2.0 and classified as problematic. Affected by this vulnerability is an unknown functionality of the file pkg/plugins/gateway/prefixcacheindexer/hash.go of the component Prefix Caching. The manipulation leads to insufficiently random values. The...

CVE-2025-1953 vLLM AIBrix Prefix Caching hash.go random values

A vulnerability has been found in vLLM AIBrix 0.2.0 and classified as problematic. Affected by this vulnerability is an unknown functionality of the file pkg/plugins/gateway/prefixcacheindexer/hash.go of the component Prefix Caching. The manipulation leads to insufficiently random values. The...

CVE-2025-1953

CVE-2025-1953 affects vLLM AIBrix 0.2.0. The issue resides in the Prefix Caching component, specifically file pkg/plugins/gateway/prefixcacheindexer/hash.go, where manipulation leads to insufficiently random values. Public documents describe the vulnerability as having a high attack complexity an...

CVE-2025-1953 vLLM AIBrix Prefix Caching hash.go random values

A vulnerability has been found in vLLM AIBrix 0.2.0 and classified as problematic. Affected by this vulnerability is an unknown functionality of the file pkg/plugins/gateway/prefixcacheindexer/hash.go of the component Prefix Caching. The manipulation leads to insufficiently random values. The...

CVE-2025-25183

A flaw was found in the vllm package. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. The impact of a collision would be using a cache that was generated using different content...

PYSEC-2025-62

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-i...

PYSEC-2025-62

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-i...

CVE-2025-25183 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm, py3.10-vllm-cuda-11.8...

CVE-2025-25183

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-i...

CVE-2025-25183 vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-i...

CVE-2025-25183

CVE-2025-25183 affects vLLM (prefix cache) where malicious inputs can trigger Python 3.12’s hash(None) behaving as a predictable constant, enabling hash collisions in the prefix cache. This may allow cache entries created from one prompt to be reused for another, causing unintended behavior in re...

CVE-2025-25183 vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-i...