CVE-2026-33865 Stored XSS via unsafe YAML parsing in MLflow

MLflow is vulnerable to Stored Cross-Site Scripting XSS caused by unsafe parsing of YAML-based MLmodel artifacts in its web interface. An authenticated attacker can upload a malicious MLmodel file containing a payload that executes when another user views the artifact in the UI. This allows actio...

Benchmarking-Agent-Architectures

Benchmarking Agent Architectures for LLM-Based Exploit Gener...

Important: 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...

Flowise AI Agent Builder Under Active CVSS 10.0 RCE Exploitation; 12,000+ Instances Exposed

Threat actors are exploiting a maximum-severity security flaw in Flowise , an open-source artificial intelligence AI platform, according to new findings from VulnCheck. The vulnerability in question is CVE-2025-59528 CVSS score: 10.0, a code injection vulnerability that could result in remote cod...

NVIDIA Triton Inference Server 路径遍历漏洞

NVIDIA Triton Inference Server is an open-source software developed by NVIDIA Corporation. It helps standardize model deployment and provide fast, scalable AI capabilities in production environments. NVIDIA Triton Inference Server has a path traversal vulnerability. This vulnerability arises from...

PT-2026-30869

Name of the Vulnerable Software and Affected Versions Django versions 6.0 through 6.0.3, 5.2 through 5.2.12, and 4.2 through 4.2.29 Description A flaw exists in the permission validation process for inline model instances within GenericInlineModelAdmin when handling forged POST data. This could...

Hybrid ResNet-1D-BiGRU with Multi-Head Attention for Cyberattack Detection in Industrial IoT Environments

This study introduces a hybrid deep learning model for intrusion detection in Industrial IoT IIoT systems, combining ResNet-1D, BiGRU, and Multi-Head Attention MHA for effective spatial-temporal feature extraction and attention-based feature weighting. To address class imbalance, SMOTE was applie...

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents

With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may impact the agent's performance. To address the challenge,...

PT-2026-30932

NVIDIA Triton Inference Server contains a vulnerability in triton server where an attacker may cause an information disclosure by uploading a model configuration. A successful exploit of this vulnerability may lead to information disclosure or denial of service...

LanG -- a Governance-Aware Agentic AI Platform for Unified Security Operations

Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that current Security Information Event Management and Extended Detection and Response systems only partially address through fragmented tools. This paper...

ClawLess: A Security Model of AI Agents

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to regulate agent behavior through training or prompting, which...

PT-2026-31030

Name of the Vulnerable Software and Affected Versions MCP Java SDK versions prior to 1.0.0 Description The MCP Java SDK contains a DNS rebinding vulnerability. This allows an attacker to access a locally or network-private MCP server via a victim's browser. An attacker can then make any tool call...

PT-2026-30820

Name of the Vulnerable Software and Affected Versions MLflow versions through 3.10.1 Description MLflow is susceptible to Stored Cross-Site Scripting XSS due to unsafe parsing of YAML-based MLmodel artifacts within its web interface. An authenticated attacker can upload a malicious MLmodel file...

PT-2026-30821

Name of the Vulnerable Software and Affected Versions MLflow versions prior to 3.10.1 Description An authorization bypass exists in the AJAX endpoint used to download saved model artifacts. Due to missing access-control validation, a user without permissions to a specific experiment can directly...

MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library

Network Intrusion Detection Systems NIDS face important limitations. Signature-based methods are effective for known attack patterns, but they struggle to detect zero-day attacks and often miss modified variants of previously known attacks, while many machine learning approaches offer limited...

Your LLM Agent Can Leak Your Data: Data Exfiltration Via Backdoored Tool Use

Tool-use large language model LLM agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats, the risk of systematic data exfiltration by backdoored...

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of automation and powerful personalization, they also expose...

Django 安全漏洞

Django is a Python-based open-source web framework developed by the Django Foundation. This framework includes an object-oriented mapper, view system, template system, etc. Versions of Django prior to 6.0.4, 5.2.13, and 4.2.30 contained security vulnerabilities. These vulnerabilities stemmed from...

SUSE CVE-2026-33032

Nginx UI is a web user interface for the Nginx web server. In versions 2.3.5 and prior, the nginx-ui MCP Model Context Protocol integration exposes two HTTP endpoints: /mcp and /mcpmessage. While /mcp requires both IP whitelisting and authentication AuthRequired middleware, the /mcpmessage endpoi...

SUSE CVE-2026-33990

Docker Model Runner DMR is software used to manage, run, and deploy AI models using Docker. Prior to version 1.1.25, Docker Model Runner contains an SSRF vulnerability in its OCI registry token exchange flow. When pulling a model, Model Runner follows the realm URL from the registry's...