PYSEC-2026-2020 vLLM vulnerable to Server-Side Request Forgery (SSRF) through MediaConnector

Summary A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods obtain and process media from URLs provided by users, using different Python parsing libraries when restrictin...

PYSEC-2026-2018 vLLM deserialization vulnerability leading to DoS and potential RCE

Summary A memory corruption vulnerability that leading to a crash denial-of-service and potentially remote code execution RCE exists in vLLM versions 0.10.2 and later, in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using...

PYSEC-2026-2013 vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server

Summary A resource-exhaustion denial-of-service vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the chattemplate and chattemplatekwargs parameters. If an attacker can supply these parameters to the API, they can cause a...

PYSEC-2026-2026 vLLM is vulnerable to timing attack at bearer auth

Summary The API key support in vLLM performed validation using a method that was vulnerable to a timing attack. This could potentially allow an attacker to discover a valid API key using an approach more efficient than brute force. Details...

PYSEC-2026-2011 vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class

Summary A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows...

PYSEC-2026-2021 vllm API endpoints vulnerable to Denial of Service Attacks

Summary A Denial of Service DoS vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making ...

PYSEC-2026-2014 vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

Summary An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

PYSEC-2026-2023 vLLM Tool Schema allows DoS via Malformed pattern and type Fields

Summary The vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference...

PYSEC-2026-2016 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...

Data exposure via ZeroMQ on multi-node vLLM deployment

ImpactIn 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 across...

PYSEC-2026-2025 vLLM Denial of Service via the best_of parameter

A vulnerability was found in the ilab model serve component, where improper handling of the bestof parameter in the vllm JSON web API can lead to a Denial of Service DoS. The API used for LLM-based sentence or chat completion accepts a bestof parameter to return the best completion from several...

Uncaught Exception

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Uncaught Exception through the rejection sampler process. An attacker can cause the engine worker to crash and abort concurrent requests by sending...

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 the request.file.read process. An attacker can exhaust system memory or cause process...

Reachable Assertion

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Reachable Assertion via the /v1/completions endpoint when processing pure prompt embeds with M-RoPE models. An attacker can cause the server to cras...

PYSEC-2026-2303

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

PYSEC-2026-2303

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

CVE-2026-55514

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

CVE-2026-54234

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then convert...

CVE-2026-55646

vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLMMAXAUDIOCLIPFILESIZEMB...

CVE-2026-55514

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...