GHSA-63HW-FMQ6-XXG2 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

GHSA-XCGM-R5H9-7989 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

CVE-2026-54279 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

CVE-2026-54280 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

GHSA-4FVR-RGM6-GQMC vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

CVE-2026-54276 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

CVE-2026-54273 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

CVE-2026-54277 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

CVE-2026-54274 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

CVE-2026-54275 vulnerabilities

Vulnerabilities for packages: text-generation-inference, open-webui, awx, apache-beam-python-3.12-sdk, apache-beam-python-3.13-sdk, dask-kubernetes-fips, metaflow-service-fips, mlflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow, mlflow-fips,...

GHSA-537C-GMF6-5CCF vulnerabilities

Vulnerabilities for packages: pgadmin4, ansible-operator-fips, openstack-tempest-2026.1, awx, openstack-horizon-2026.1, label-studio, ansible-operator, vast-csi, openstack-keystone-2026.1, openstack-placement-2026.1, crossplane-function-pythonic, kubeflow-volumes-web-app, dask-kubernetes-fips,...

HTTP Request Smuggling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to HTTP Request Smuggling via improper validation of the Host header in the request scope. An attacker can gain unauthorized access to API endpoints by...

vLLM: OpenAI auth bypass

Summary A vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware, which was discovered during @x41sec's source code audit. It allows to use the API without providing the configured VLLMAPIKEY or...

GHSA-94F4-HR76-P5J6 vLLM: OpenAI auth bypass

Summary A vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware, which was discovered during @x41sec's source code audit. It allows to use the API without providing the configured VLLMAPIKEY or...

vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution

Summary An assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode python -O or PYTHONOPTIMIZE=1. Details vLLM uses ...

CVE-2026-5497

A flaw was found in vLLM. An attacker can exploit this vulnerability by sending a specially crafted API request containing an excessive number of base64-encoded JPEG frames within a data URL. This unbounded processing of frames in the VideoMediaIO.loadbase64 method leads to an Out-of-Memory OOM...

PT-2026-50144

Name of the Vulnerable Software and Affected Versions vLLM versions 0.3.0 through 0.21.0 Description An authentication bypass exists in the OpenAI API AuthenticationMiddleware due to improper trust in the reconstructed URL path from the ASGI scope. The url path is derived from a URL object...

CVE-2026-5497

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory OOM Denial of Service DoS attack due to unbounded frame count processing in the VideoMediaIO.loadbase64 method. When processing video/jpeg data URLs, the method splits the base64 data string on commas to extract individual JPEG fram...

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 via the VideoMediaIO.loadbase64 function. An attacker can cause the server to exhaust memory...

Use of Incorrectly-Resolved Name or Reference

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Use of Incorrectly-Resolved Name or Reference through several model loading paths. An attacker can make the server load a different Hugging Face...