EUVD-2026-31493

The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trustremotecode=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.frompretrained to import and execute arbitrary Python files included in any model pulled fr...

CVE-2026-5817: Inclusion of Functionality from Untrusted Control Sphere

The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trustremotecode=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.frompretrained to import and execute arbitrary Python files included in any model pulled fr...

PT-2026-42830

Name of the Vulnerable Software and Affected Versions Docker Model Runner on macOS affected versions not specified Description The vllm-metal inference backend unconditionally sets trust remote code=True when loading model tokenizers and operates without sandboxing. This allows the...

CVE-2026-44222

vLLM is an inference and serving engine for large language models LLMs. From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder...

CVE-2026-44223

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

PYSEC-2026-145

vLLM is an inference and serving engine for large language models LLMs. From to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash ...

CVE-2026-44223

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

CVE-2026-44223 vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

CVE-2026-44222 vLLM: Remote DoS via Special-Token Placeholders

vLLM is an inference and serving engine for large language models LLMs. From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder...

CVE-2026-44222

CVE-2026-44222 (vLLM) affects vLLM versions 0.6.1 through 0.19.x where a token-injection vulnerability in multimodal processing allows unauthenticated text prompts containing special tokens to be interpreted as control. When image/video placeholder sequences are provided without corresponding dat...

CVE-2026-44222

vLLM is an inference and serving engine for large language models LLMs. From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder...

CVE-2026-44222 vLLM: Remote DoS via Special-Token Placeholders

vLLM is an inference and serving engine for large language models LLMs. From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder...

CVE-2026-44222

vLLM is an inference and serving engine for large language models LLMs. From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder...

CVE-2026-44222: Improper Validation of Array Index

vLLM is an inference and serving engine for large language models LLMs. From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder...

CVE-2026-44223: Incorrect Calculation of Buffer Size

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

vLLM 安全漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.20.0 contained a security vulnerability. This vulnerability stemmed from the extracthiddenstates speculative decoding proposal, which returned tensor...

vLLM 输入验证错误漏洞

vLLM is an open-source inference and service engine designed for LLM models, featuring high throughput and efficient memory usage. Versions of vLLM prior to 0.6.1 to 0.20.0 contained a vulnerability related to input validation errors. This vulnerability stemmed from token injection issues during...

Incorrect Type Conversion or Cast

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Incorrect Type Conversion or Cast through the extracthiddenstates speculative decoding. An attacker can cause the server to crash and disrupt servic...

vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

Summary The extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters...

GHSA-83VM-P52W-F9PW vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

Summary The extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters...