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 Mooncake integration. An attacker can execute arbitrary code by sending malicious payloads to a pickle base...

CVE-2025-32444

vLLM (0.6.5–0.8.4) with mooncake integration is vulnerable to remote code execution due to pickle-based serialization over unsecured ZeroMQ sockets that were listening on all interfaces. This could be exploited remotely; non-mooncake deployments are not affected. The issue is fixed in vLLM 0.8.5....

CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerab...

Inefficient Algorithmic Complexity

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Inefficient Algorithmic Complexity through the inputprocessorforphi4mm function. An attacker can cause the application to consume excessive resource...

CVE-2025-46560 vLLM phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens...

CVE-2025-46560 vLLM phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens...

CVE-2025-46560 vLLM phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens...

CVE-2025-30202 Data exposure via ZeroMQ on multi-node vLLM deployment

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-no...

CVE-2025-30202 Data exposure via ZeroMQ on multi-node vLLM deployment

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-no...

CVE-2025-30202

CVE-2025-30202 affects vLLM versions 0.5.2 up to 0.8.4 (prior to 0.8.5) in multi-node deployments. The root cause is an XPUB ZeroMQ socket bound to ALL interfaces on the primary host used for tensor parallelism, which can be accessed by any client with network access. This allows potential data e...

CVE-2025-30202 Data exposure via ZeroMQ on multi-node vLLM deployment

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-no...

vLLM 安全漏洞

vLLM is a high throughput and memory efficient inference and service engine for LLM from the vLLM open source. A security vulnerability exists in vLLM versions prior to 0.8.0 through 0.8.5, which stems from inefficiencies in the input preprocessing logic that could lead to resource exhaustion...

vLLM 代码问题漏洞

vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. A code issue vulnerability exists in vLLM versions prior to 0.6.5 to 0.8.5, which stems from the use of pickle-based serialization and could lead to remote code execution...

vLLM Vulnerable to Remote Code Execution via Mooncake Integration

Impacted Deployments Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable. Description vLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were...

Data exposure via ZeroMQ on multi-node vLLM deployment

Impact In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL interfaces. While the socket is always opened for a multi-node deployment, it is only used when doing tensor parallelism acros...

PT-2025-18215

Name of the Vulnerable Software and Affected Versions vLLM versions 0.5.2 through 0.8.5 Description The issue affects vLLM, a high-throughput and memory-efficient inference and serving engine for LLMs. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes,...

Denial Of Service (DoS)

vllm is vulnerable to Denial of Service DoS. The vulnerability is due to unbounded in-memory cache growth due to allowing unique schema requests to continually populate the grammar cache, potentially exhausting system RAM...

GHSA-GGPF-24JW-3FCW CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0

Description https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 reported a vulnerability where loading a malicious model could result in code execution on the vllm host. The fix applied to specify weightsonly=True to calls to torch.load did not solve the problem prior to...

GHSA-HF3C-WXG2-49Q9 vLLM vulnerable to Denial of Service by abusing xgrammar cache

Impact This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 The xgrammar library is the default backend used by vLLM to support...

vLLM vulnerable to Denial of Service by abusing xgrammar cache

Impact This report is to highlight a vulnerability in XGrammar, a library used by the structured output feature in vLLM. The XGrammar advisory is here: https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-389x-67px-mjg3 The xgrammar library is the default backend used by vLLM to support...