PT-2026-67793

Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server for Linux affected versions not specified Description An issue exists in the Triton MLflow plugin where providing a specific path in the model name allows a user to read, write to, or modify files located outside...

CVE-2026-47487: Improper Limitation of a Pathname to a Restricted Directory

NVIDIA Triton Inference Server for Linux contains a vulnerability where a user could cause files outside the model repository to be read, written to, or modified by providing a path in the model name to the Triton MLflow plugin. A successful exploit of this vulnerability might lead to denial of...

Antares: Foundation Models for Agentic Vulnerability Localization

Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We present Antares, a family of compact language models 350M, 1B, and 3B parameters for agentic vulnerability localization...

SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems Via Deterministic Side Channels

Modern large language models LLMs exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researchers have leveraged this property to optimize LLM serving systems by omitting weight accesses and computations pertaining to inactive neurons...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2026-9335 via keras (2.12.0rc0)

keras PYPI version 2.12.0rc0 is affected by a known vulnerability. The following packages have a transitive dependency on keras and may be impacted: - mlopspython-inference =67580760626172675.0.0, =757069802391466481559610331145 Source cves: CVE-2026-9335 Source advisory: OSV:GHSA-M8WH-29WM-52MV...

CVE-2026-45376 Decidim: Admin user search allows SQL injection through similarity-based sorting

Decidim is a participatory democracy framework. Prior to 0.30.9, from 0.31.0 before 0.31.5, and in 0.32.0.rc1 before 0.32.0.rc2, the GET /admin/organization/users search interpolates params:term into raw Arel.sql ORDER BY similarity expressions before sanitization, allowing an authenticated...

CVE-2026-45376 Decidim: Admin user search allows SQL injection through similarity-based sorting

Decidim is a participatory democracy framework. Prior to 0.30.9, from 0.31.0 before 0.31.5, and in 0.32.0.rc1 before 0.32.0.rc2, the GET /admin/organization/users search interpolates params:term into raw Arel.sql ORDER BY similarity expressions before sanitization, allowing an authenticated...

CVE-2026-15971

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

EUVD-2026-51262

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

CVE-2026-15971 CVE-2026-15971

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

CVE-2026-15971 CVE-2026-15971

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

CVE-2026-15971

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

CVE-2026-15971

The SGLang open-source framework for serving large language models (LLMs) contains a Remote Code Execution (RCE) vulnerability. When the optional dumper subsystem is enabled and the DUMPER_SERVER_PORT variable is set, an attacker can achieve a sandbox escape . This allows for arbitrary code execu...

CVE-2026-15971 CVE-2026-15971

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

PT-2026-66559

Name of the Vulnerable Software and Affected Versions SGLang affected versions not specified Description An issue exists when the optional dumper subsystem is enabled and the DUMPER SERVER PORT variable is set. This allows for a sandbox escape, which can lead to remote code execution during...

CVE-2026-15971: Improper Neutralization of Directives in Dynamically Evaluated Code

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPERSERVERPORT is set, enabling code execution on inference requests...

Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

Autonomous multi-agent systems AMAS built on large language models LLMs, such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively...

CVE-2026-56764

A flaw was found in Hono. This vulnerability, a timing attack, exists in the basicAuth and bearerAuth middlewares due to a non-constant-time string comparison. A remote attacker could exploit the early termination of string equality checks to infer valid credentials by precisely measuring respons...

vLLM OpenAI-Compatible API - Unauthenticated Exposure Detection

Detects a vLLM inference server exposing its OpenAI-compatible API without authentication. The /v1/models endpoint returns the list of served models and is reachable by any unauthenticated client, allowing model enumeration and unauthorized inference resource abuse / cost and information exposure...

Security Bulletin: IBM Watson Speech Services Cartridge is vulnerable to data inference in Spring Data Relational [CVE-2026-41697]

Summary IBM Watson Speech Services Cartridge is vulnerable to data inference in Spring Data Relational, due to a failure to properly escape binding values of externally-controlled input hat can allow an attacker can supply wildcard characters CVE-2026-41697. Spring Data Relational, is used as par...