CVE-2026-4944

The provided documents describe a vulnerability in vllm-project/vllm version 0.14.1 where trust_remote_code is hardcoded to True in nemotron_vl.py and kimi_k25.py, bypassing user-specified --trust-remote-code=False and enabling remote code execution via malicious HuggingFace model repositories. T...

CVE-2026-4944 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control

vllm-project/vllm version 0.14.1 contains a vulnerability where the trustremotecode=True parameter is hardcoded in two model implementation files vllm/modelexecutor/models/nemotronvl.py and vllm/modelexecutor/models/kimik25.py. This bypasses the user's explicit --trust-remote-code=False setting,...

Improper Resource Shutdown or Release

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Improper Resource Shutdown or Release via the OpenAI-compatible Serving Path component. An attacker can cause the service to become unavailable by...

EUVD-2026-31810

A vulnerability was identified in vllm-project vllm 0.19.0. This issue affects some unknown processing of the component OpenAI-compatible Serving Path. Such manipulation leads to denial of service. It is possible to launch the attack remotely. The exploit is publicly available and might be used...

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...

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...

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...

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 Vulnerable to Remote DoS via Special-Token Placeholders

Summary This report explains 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 sequences supplied without matching data cause vLLM to index into empty grids during...

Exploit for Server-Side Request Forgery in Vllm

No d...

GHSA-X368-4G9H-FVV4 vLLM makes Use of Uninitialized Resource

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function hasmambalayers of the file vllm/v1/kvcacheinterface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is...

vLLM makes Use of Uninitialized Resource

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function hasmambalayers of the file vllm/v1/kvcacheinterface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is...

ado-vllm-performance (>=1.2.2 <=1.3.3), agentclinic (=0.1.0) +37 more potentially affected by CVE-2026-7141 via vllm (>=0.10.0 <=0.19.0)

vllm PYPI version =0.10.0, =1.2.2, =0.0.0, =2.3.5, =0.2.0, =0.1.0, =1.0.1rc1, =0.0.4, =0.1.0, =0.3.9, =0.5.2, =0.1.0, =0.1.5, =0.2.0 - gfmrag =2.0.0 and more Source cves: CVE-2026-7141 Source advisory: OSV:GHSA-X368-4G9H-FVV4...

CVE-2026-7141

A vulnerability was found in vllm up to 0.19.0. The affected element is the function hasmambalayers of the file vllm/v1/kvcacheinterface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is...

EUVD-2026-25892

A vulnerability was found in vllm up to 0.19.0. The affected element is the function hasmambalayers of the file vllm/v1/kvcacheinterface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is...

CVE-2026-34755 vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing

vLLM is an inference and serving engine for large language models LLMs. From 0.7.0 to before 0.19.0, the VideoMediaIO.loadbase64 method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The numframes...

Server-side Request Forgery (SSRF)

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the downloadbytesfromurl function. An attacker can cause the server to make arbitrary HTTP or HTTPS requests to...

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 due to the lack of upper bound validation on the n parameter in the request handling process. A...

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 0.10.1 to 0.18.0 contained a security vulnerability. This vulnerability stemmed from the hardcoding of trustremotecode=True in two model implementation...

CVE-2026-27893 vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

vLLM is an inference and serving engine for large language models LLMs. Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode trustremotecode=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This...