vLLM <= 0.23.0 - Anthropic Router Heap Address Information Leak

vLLM = 0.23.0 incompletely fixes CVE-2026-22778. The original fix added sanitizemessage to the OpenAI router but the Anthropic-compatible router /v1/messages echoes strexc directly. id: CVE-2026-54236 info: name: vLLM = 0.23.0 - Anthropic Router Heap Address Information Leak author: kenlacroix...

CVE-2026-90878

A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template Rendering. This manipulation of the argument chattemplate causes resource consumption. The attack can be initiated remotely. The exploit...

CVE-2026-90878

A flaw was found in vllm-project vLLM. A remote attacker could exploit a vulnerability in the Jinja Template Rendering component by manipulating the chattemplate argument. This manipulation leads to excessive resource consumption, potentially causing a Denial of Service DoS condition for the...

CVE-2026-90878

vLLM (vllm-project) versions up to 0.27.1 are affected by a resource consumption vulnerability in the Jinja Template Rendering component of the /v1/chat/completions endpoint. The root cause is manipulation of the chat_template argument, allowing a remote attacker with low privileges to trigger ex...

EUVD-2026-78268

A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template Rendering. This manipulation of the argument chattemplate causes resource consumption. The attack can be initiated remotely. The exploit...

CVE-2026-90878 vllm-project vLLM Jinja Template Rendering completions resource consumption

A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template Rendering. This manipulation of the argument chattemplate causes resource consumption. The attack can be initiated remotely. The exploit...

PT-2026-91857

A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template Rendering. This manipulation of the argument chat template causes resource consumption. The attack can be initiated remotely. The exploit...

CVE-2024-11040

CVE-2024-11040 vllm-project vllm version 0.5.2.2 is vulnerable to Denial of Service attacks...

CVE-2026-90713

A security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The attack is only possib...

CVE-2026-90713

A flaw was found in vLLM and tiktoken. A local attacker can exploit a vulnerability within the TiktokenTokenizer::new function of the tiktoken vocab File Handler component. This can lead to a denial of service, making the affected system unavailable...

EUVD-2026-77463

A security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The attack is only possib...

CVE-2026-90713 vllm-project vLLM tiktoken vocab File mod.rs new denial of service

A security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The attack is only possib...

CVE-2026-90713

A denial of service vulnerability exists in vLLM (vllm-project) up to version 0.29.0 . The flaw is in the TiktokenTokenizer::new function within the tiktoken vocab File Handler component (file rust/src/text/src/backend/hf/mod.rs). An attacker with local access can trigger a denial of service by m...

PT-2026-91176

A security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The attack is only possib...

CVE-2026-90554

vLLM versions =0.10.2 and 0.28.0 do not apply any audio decode-size or duration limit when extracting audio from video input for NanoNemotronVL models. In nanonemotronvl.py, extractaudiofromvideos calls loadaudiopyavBytesIOvideobytes without the maxdurations or maxdecodebytes parameters, so neith...

CVE-2026-90555

vLLM versions before 0.28.0 fail to validate audio sample rate headers in the transcription endpoint, allowing authenticated clients to bypass duration checks. Attackers can submit forged FLAC headers with inflated sample rates to trigger excessive memory allocation and crash the API server proce...

CVE-2026-90553

vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trustremotecode parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processingllavaonevision2.py that executes with...

CVE-2026-90553

A flaw was found in vLLM. The LlavaOnevision2 processor loader incorrectly ignores the trustremotecode parameter, which is designed to prevent the execution of untrusted code. This oversight allows an attacker to craft a malicious model containing arbitrary code. When such a model is loaded, the...

CVE-2026-90555

A flaw was found in vLLM. An authenticated client can exploit this vulnerability by submitting forged FLAC Free Lossless Audio Codec headers with an inflated sample rate to the transcription endpoint. This bypasses duration checks, leading to excessive memory allocation within the API server...

CVE-2026-90554

A flaw was found in vLLM. This vulnerability allows a remote attacker to cause a denial of service by providing a specially crafted, highly compressed video as multimodal input when the NanoNemotronVL model is configured to use audio from video. The lack of proper size or duration limits during...