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...

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...

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...

CVE-2026-33866: Missing Authorization

MLflow is vulnerable to an authorization bypass affecting the AJAX endpoint used to download saved model artifacts. Due to missing access‑control validation, a user without permissions to a given experiment can directly query this endpoint and retrieve model artifacts they are not authorized to...

Django security vulnerabilities

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...

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-2026-30869

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...

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,...

CVE-2026-24147: Improper Limitation of a Pathname to a Restricted Directory

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...

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...

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...

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...

CVE-2026-5470

A security vulnerability has been detected in mixelpixx Google-Research-MCP 1e062d7bd887bfe5f6e582b6cc288bb897b35cf2/ca613b736ab787bc926932f59cddc69457185a83. This issue affects the function extractContent of the file src/services/content-extractor.service.ts of the component Model Context Protoc...

Why Every Enterprise Needs a Risk Operations Center (ROC)

Enterprise security has long optimized for speed of response over prevention of risk. At Qualys, we recognized early that this left half the problem unsolved, and we have spent years building the operational frameworks to close that gap. The Risk Operations Center is the result. Here is a scenari...

CVE-2026-35173

Chyrp Lite is an ultra-lightweight blogging engine. Prior to 2026.01, an IDOR / Mass Assignment issue exists in the Post model that allows authenticated users with post editing permissions Edit Post, Edit Draft, Edit Own Post, Edit Own Draft to modify posts they do not own and do not have...

CVE-2026-35050

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.1.1, users can save extention settings in "py" format and in the app root directory. This allows to overwrite python files, for instance the "download-model.py" file could be overwritten. Then, thi...

ng-model-gym (>=0.3.0, <=0.4.0) potentially affected by CVE-2026-26981 via openexr (3.4.4)

openexr PYPI version 3.4.4 is affected by a known vulnerability. The following packages have a transitive dependency on openexr and may be impacted: - ng-model-gym =0.3.0, =0.4.0 Source cves: CVE-2026-26981 Source advisory: OSV:GHSA-Q6VJ-WXVF-5M8C...

ng-model-gym (>=0.3.0, <=0.4.0) potentially affected by CVE-2026-26981 via openexr (3.4.4)

openexr PYPI version 3.4.4 is affected by a known vulnerability. The following packages have a transitive dependency on openexr and may be impacted: - ng-model-gym =0.3.0, =0.4.0 Source cves: CVE-2026-26981 Source advisory: GHSA-Q6VJ-WXVF-5M8C...

Regular Expression without Anchors

Overview Affected versions of this package are vulnerable to Regular Expression without Anchors in the parseModelURL function in Ollama Engine startup probe that allows shell metacharacters like ;, |, $, and backticks. An attacker can execute arbitrary operating system commands by supplying a...