623 matches found
CVE-2026-47630
CVE-2026-47630 — NVIDIA Triton Inference Server: arbitrary dlopen via TRITONBATCHSTRATEGYPATH Absolute path traversal in the custom batching-strategy loader of triton-inference-server/core. A model configuration parameter is passed unvalidated to dlopenRTLDNOW | RTLDLOCAL, so anyone able to...
GHSA-MF5V-W3W3-F6CG vulnerabilities
Vulnerabilities for packages: spamcheck, datadog-agent, py3-opentelemetry-semantic-conventions-ai, dbt-snowflake, sentry, airflow-postgres-fips, azureml-inference-server-http-fips, label-studio...
CVE-2026-126360 vulnerabilities
Vulnerabilities for packages: spamcheck, datadog-agent, py3-opentelemetry-semantic-conventions-ai, dbt-snowflake, sentry, airflow-postgres-fips, azureml-inference-server-http-fips, label-studio...
CVE-2023-43654
CVE-2023-43654 ShellTorch is a chain of 3 Critical Vulnerabilities in PyTorch TorchServe - the default inference server of PyTorch. This is an End-to-End POC for an SSRF vulnerability which leads to Arbitrary Remote Code Execution from the network 1. Run TorchServe 0.8.1 docker run -d --rm -it -p...
cve-2026-47627
CVE-2026-47627 — NVIDIA Triton Inference Server Path Traversal → DoS Zip-Slip Complete research writeup & PoC in this repo image nvcr.io/nvidia/tritonserver:26.05-py3 / server v2.69.0. Repo is set up to always be explicit so PoC works without restart via gRPC. Table of Contents 1. CVE Summary 2...
CVE-2026-24207
CVE-2026-24207 — NVIDIA Triton SageMaker Auth Bypass to Unauth RCE Unauthenticated attackers can reach the model-management surface of NVIDIA Triton Inference Server on the SageMaker and Vertex AI HTTP ports — bypassing the operator's --http-restricted-api configuration. Combined with the SageMak...
Critical: Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (CUDA)
Red Hat AI Inference Server 3.2.2 CUDA is now available. Red Hat® AI Inference Server...
Critical: Red Hat Security Advisory: Red Hat AI Inference Server Model Optimization Tools 3.2.2 (CUDA)
Red Hat AI Inference Server Model Optimization Tools 3.2.2 CUDA is now available. Red Hat® AI Inference Server Model Optimization Tools...
Critical: Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (ROCm)
Red Hat AI Inference Server 3.2.2 ROCm is now available. Red Hat® AI Inference Server...
PT-2026-115337
EVENING GLOBAL SUPER INTELLIGENCE ANALYSIS REPORT By Ed Hernandez | Keystone Pulse Media / Global Media Center October 15, 2026 Executive Evening Pulse Edition: The Giveaway Good evening. Thursday is one story told twice. The chips sold off. Reuters reported the Philadelphia Semiconductor Index...
EnergizeLab FastAPI AI inference server has a path traversal vulnerability
The EnergizeLab FastAPI AI inference server has a security vulnerability. This vulnerability stems from the AI skills upload endpoint not requiring authentication and not restricting the path of the uploaded files. This allows unauthorized remote attackers to exploit path traversal to write...
EnergizeLab FastAPI AI inference server authorization issue vulnerability
The EnergizeLab FastAPI AI inference server has a vulnerability related to authorization. This vulnerability arises from the lack of authentication for the AI model management function, which may allow unauthenticated remote attackers to modify the AI model configuration and switch the model that...
Anytime-Valid Detection of LLM Weight Exfiltration
A compromised LLM inference server can leak model weights by encoding payload bits in otherwise plausible token choices. A replay of the same prompt in a trusted server can expose such deviations, but benign numerical nondeterminism also causes token mismatches. Patient attackers can therefore hi...
Exposure of Resource to Wrong Sphere
Overview docling is a SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications. Affected versions of this package are vulnerable to Exposure of Resource to Wrong Sphere via the KserveV2OcrModel class in...
NVIDIA Triton Inference Server Auth Bypass (CVE-2026-24207)
Exploits CVE-2026-24207 in NVIDIA Triton Inference Server = 26.02: unauthenticated access to restricted HTTP APIs including /models and model management endpoints. !/usr/bin/env python3 -- coding: utf-8 -- """NVIDIA Triton Inference Server auth bypass CVE-2026-24207.""" import json from kittysplo...
GHSA-42VR-XJ54-VC7V vulnerabilities
Vulnerabilities for packages: openstack-glance-2025.1, openstack-horizon-2025.2, openstack-placement-2026.1-fips, openstack-horizon-2025.2-fips, lmcache-cuda-12.8, lmcache-cuda-13.0, openstack-cinder-2026.1, authentik-fips, kserve, kserve-huggingfaceserver-cuda-13.3, openstack-horizon-2026.1,...
CVE-2026-101918 vulnerabilities
Vulnerabilities for packages: openstack-glance-2025.1, openstack-horizon-2025.2, openstack-placement-2026.1-fips, openstack-horizon-2025.2-fips, lmcache-cuda-12.8, lmcache-cuda-13.0, openstack-cinder-2026.1, authentik-fips, kserve, kserve-huggingfaceserver-cuda-13.3, openstack-horizon-2026.1,...
GHSA-HJ66-6F7G-4R5V vulnerabilities
Vulnerabilities for packages: dask-kubernetes-fips, jupyter-base-notebook, dbt-bigquery, authentik-fips, kserve, kserve-huggingfaceserver-cuda-13.3, openstack-keystone-2025.1-fips, azureml-inference-server-http, metaflow-service-fips, open-webui, litellm, pgadmin4-fips, pgadmin4, kubeflow,...
GHSA-HXM8-2XGR-2P9M vulnerabilities
Vulnerabilities for packages: openstack-glance-2025.1, openstack-horizon-2025.2, openstack-placement-2026.1-fips, openstack-horizon-2025.2-fips, openstack-cinder-2026.1, authentik-fips, kserve, kserve-huggingfaceserver-cuda-13.3, openstack-horizon-2026.1, openstack-keystone-2025.1-fips,...
GHSA-W2CX-738M-MC7W vulnerabilities
Vulnerabilities for packages: openstack-glance-2025.1, openstack-horizon-2025.2, openstack-placement-2026.1-fips, openstack-horizon-2025.2-fips, openstack-cinder-2026.1, authentik-fips, kserve, kserve-huggingfaceserver-cuda-13.3, openstack-horizon-2026.1, openstack-keystone-2025.1-fips,...