Lucene search
+L

1107 matches found

Chainguard
Chainguard
added 2026/08/24 8:25 p.m.21 views

GHSA-3WW4-5JV9-J5GM vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

5.8AI score
SaveExploits0
Chainguard
Chainguard
added 2026/08/24 8:25 p.m.27 views

GHSA-33CG-GXV8-3P8G vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

5.8AI score
SaveExploits0
Chainguard
Chainguard
added 2026/08/24 8:25 p.m.26 views

GHSA-RWXX-MRJM-WC2M vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

5.8AI score
SaveExploits0
Chainguard
Chainguard
added 2026/08/24 8:25 p.m.21 views

CVE-2026-41523 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

7.5CVSS5.8AI score0.00913EPSS
SaveExploits1
Chainguard
Chainguard
added 2026/08/24 8:25 p.m.24 views

CVE-2026-55514 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

7.1CVSS5.8AI score0.00665EPSS
SaveExploits0
Chainguard
Chainguard
added 2026/08/24 8:25 p.m.27 views

CVE-2026-55574 vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-12.9, tritonserver-backend-vllm-cuda-13.0...

8.7CVSS5.8AI score0.00583EPSS
SaveExploits0
RedHat Linux
RedHat Linux
added 2026/08/24 4:51 p.m.51 views

Important: Red Hat Security Advisory: Red Hat AI Inference Server 3.3.6 (CUDA)

Red Hat AI Inference Server 3.3.6 CUDA is now available. Red Hat® AI Inference Server...

7.5CVSS5.1AI score0.00913EPSS
SaveExploits1References5
RedHat Linux
RedHat Linux
added 2026/08/20 7:58 a.m.10 views

Important: Red Hat Security Advisory: Red Hat AI Inference 3.4.4 (cuda)

Red Hat AI Inference 3.4.4 cuda is now available. Red Hat AI Inference...

7.5CVSS5.1AI score0.00913EPSS
SaveExploits2References7
RedHat Linux
RedHat Linux
added 2026/08/20 7:56 a.m.13 views

Moderate: Red Hat Security Advisory: Red Hat AI Inference Model Optimization Tools 3.4.4 (cuda)

Red Hat AI Inference Model Optimization Tools 3.4.4 cuda is now available. Red Hat AI Inference Model Optimization Tools...

5.5CVSS5.1AI score0.00182EPSS
SaveExploits0References3
Chainguard
Chainguard
added 2026/08/14 8:25 a.m.29 views

CVE-2026-57516 vulnerabilities

Vulnerabilities for packages: lmcache-cuda-12.8...

8.8CVSS5.2AI score0.00858EPSS
SaveExploits1
Chainguard
Chainguard
added 2026/08/14 8:25 a.m.58 views

GHSA-HHRP-GW25-JR43 vulnerabilities

Vulnerabilities for packages: lmcache-cuda-12.8...

5.3AI score
SaveExploits0
Chainguard
Chainguard
added 2026/08/14 8:24 a.m.21 views

GO-2025-3828 vulnerabilities

Vulnerabilities for packages: agentbeat, kubeflow-katib, nvidia-nsight-compute-13.1, newrelic-fluent-bit-output, nvidia-nsight-compute-13.0, nvidia-nsight-compute-12.9, nvidia-nsight-compute-12.8, nemo, nvidia-nsight-compute-13.2...

5.9AI score
SaveExploits0
NVD
NVD
added 2026/08/13 3:20 p.m.11 views

CVE-2026-73558

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

5.3CVSS0.00326EPSS
SaveExploits0References5
ATTACKERKB
ATTACKERKB
added 2026/08/13 3:06 p.m.10 views

CVE-2026-73558

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

5.3CVSS5.3AI score0.00326EPSS
SaveExploits0References6Affected Software1
Cvelist
Cvelist
added 2026/08/13 3:06 p.m.36 views

CVE-2026-73558 vLLM: Cross-User Data Leak Vulnerability

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

5.3CVSS0.00326EPSS
SaveExploits0References5
OSV
OSV
added 2026/08/13 3:06 p.m.33 views

CVE-2026-73558 vLLM: Cross-User Data Leak Vulnerability

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

5.3CVSS5.5AI score
SaveExploits0References7
Positive Technologies
Positive Technologies
added 2026/08/13 12:00 a.m.11 views

PT-2026-71673

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.27.0 Description An integer overflow occurs in the calculation blockIdx.x 2 d within the activation kernels.cu file. This flaw can cause the act and mul kernel function to consume input from another user within the sam...

5.3CVSS5.3AI score0.00326EPSS
SaveExploits0References14
Amazon
Amazon
added 2026/07/24 12:00 a.m.14 views

Important: cuda-compat

Issue Overview: NVIDIA Display Driver for Windows and Linux contains a vulnerability where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to denial of service, escalation of privileges, information disclosure, data tampering, and code...

7.8CVSS5.9AI score0.00197EPSS
SaveExploits0
Amazon
Amazon
added 2026/07/24 12:00 a.m.13 views

Important: cuda-drivers

Issue Overview: NVIDIA Display Driver for Windows and Linux contains a vulnerability where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to denial of service, escalation of privileges, information disclosure, data tampering, and code...

7.8CVSS5.9AI score0.00197EPSS
SaveExploits0
OSV
OSV
added 2026/07/14 8:02 p.m.16 views

MAL-2026-10617 Malicious code in cosmos-cuda (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c1a96e5776ec64356f639738134c95a2f33233a4275d2d0ddd6b174c297c64ee The sdist-only package cosmos-cuda 9999.0.0 executes a beacon function beacon'build' from setup.py during sdist build/install and beacon'import' from...

6.6AI score
SaveExploits0References2
Rows per page
Query Builder