CVE-2026-24264

NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause improper handling of highly compressed data. A successful exploit of this vulnerability might lead to denial of service...

Security Bulletin: NVIDIA Triton Inference Server - June 2026

NVIDIA has released a software update for NVIDIA® Triton Inference Server. To protect your system, clone or update this software to Triton Server r26.04 or later from the NVIDIA Triton Inference Server GitHub repo. Go to NVIDIA Product Security. Details The following table summarizes the potentia...

Missing Authorization

Overview Affected versions of this package are vulnerable to Missing Authorization in the SortingImpl.getValidSortingRules process. An attacker can infer the values of restricted fields by analyzing the order of rows returned through both JSON:API and GraphQL read paths. Remediation There is no...

CVE-2026-53923

A flaw was found in vLLM. Integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels leads to partial tensor processing. This results in the output tensor retaining previously used GPU memory, which, in multi-tenant inference deployments, can expose sensitive tensor data from other...

Critical: Red Hat Security Advisory: Red Hat AI Inference Server 3.3.5 (CUDA)

Red Hat AI Inference Server 3.3.5 CUDA is now available. Red Hat® AI Inference Server...

Critical: Red Hat Security Advisory: Red Hat AI Inference Server 3.3.5 (ROCm)

Red Hat AI Inference Server 3.3.5 ROCm is now available. Red Hat® AI Inference Server...

Critical: Red Hat Security Advisory: Red Hat AI Inference Server 3.3.5 (Spyre)

Red Hat AI Inference Server 3.3.5 Spyre is now available. Red Hat® AI Inference Server...

Important: Red Hat Security Advisory: Red Hat AI Inference Server Model Optimization Tools 3.3.5 (CUDA)

Red Hat AI Inference Server Model Optimization Tools 3.3.5 CUDA is now available. Red Hat® AI Inference Server Model Optimization Tools...

CVE-2026-54235

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.23.1rc0, ll temperature validation gates use comparison operators , which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagat...

CVE-2026-53923

vLLM is an inference and serving engine for large language models LLMs. From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels csrc/quantization/gguf/ggufkernel.cu causes partial tensor processing. The output tensor is allocated at full size via...

CVE-2026-53805

NVIDIA Spatial Intelligence Lab's SIL GEN3C contains an unauthenticated remote code execution vulnerability in the inference API server where the /request-inference and /seed-model endpoints deserialize raw HTTP request bodies using Python's pickle.loads without authentication or input validation...

CVE-2026-53805 NVIDIA SIL GEN3C Unauthenticated RCE via Pickle Deserialization in Inference API

NVIDIA Spatial Intelligence Lab's SIL GEN3C contains an unauthenticated remote code execution vulnerability in the inference API server where the /request-inference and /seed-model endpoints deserialize raw HTTP request bodies using Python's pickle.loads without authentication or input validation...

CVE-2026-53805 NVIDIA SIL GEN3C Unauthenticated RCE via Pickle Deserialization in Inference API

NVIDIA Spatial Intelligence Lab's SIL GEN3C contains an unauthenticated remote code execution vulnerability in the inference API server where the /request-inference and /seed-model endpoints deserialize raw HTTP request bodies using Python's pickle.loads without authentication or input validation...

CVE-2026-53805

CVE-2026-53805 affects NVIDIA Spatial Intelligence Lab’s GEN3C. It describes an unauthenticated remote code execution vulnerability in the inference API server, exploitable via /request-inference and /seed-model endpoints that deserialize raw HTTP bodies with Python pickle.loads() without authent...

EUVD-2026-37762

NVIDIA Spatial Intelligence Lab's SIL GEN3C contains an unauthenticated remote code execution vulnerability in the inference API server where the /request-inference and /seed-model endpoints deserialize raw HTTP request bodies using Python's pickle.loads without authentication or input validation...

vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

Summary All temperature validation gates use comparison operators , which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors tha...

PT-2026-50472

Name of the Vulnerable Software and Affected Versions vLLM versions 0.5.5 through 0.23.1rc0 Description Integer truncation of tensor dimensions in GGUF dequantize kernels within csrc/quantization/gguf/gguf kernel.cu leads to partial tensor processing. The output tensor is allocated at full size...

CVE-2026-41697

A flaw was found in Spring Data Relational. This vulnerability allows a remote attacker to perform boolean-based blind data inference by supplying wildcard characters in externally-controlled input when using StringMatcher in Query By Example QBE. This can lead to the disclosure of sensitive...

CVE-2026-53674

BuddyPress 14.4.0 contains a regular expression injection vulnerability in the activity mention resolver that, when username compatibility mode is enabled, allows attackers to manipulate a REGEXP database clause by crafting mention names containing regex metacharacters. Attackers can submit...

PT-2026-50511

Name of the Vulnerable Software and Affected Versions NVIDIA Spatial Intelligence Lab's SIL GEN3C affected versions not specified Description The inference API server contains an unauthenticated remote code execution flaw. The endpoints '/request-inference' and '/seed-model' deserialize raw HTTP...