Open WebUI Exposes System Prompt to Regular User [Non-Admin]

Summary A regular user non-admin can view the system prompt of the model which is set by an admin. Details When a regular user non-admin logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available...

CVE-2026-8597 Missing integrity verification in Triton inference handler in Amazon SageMaker Python SDK

Missing integrity verification in the Triton inference handler in Amazon SageMaker Python SDK v2 before v2.257.2 and v3 before v3.8.0 might allow a remote authenticated actor to achieve code execution in inference containers via replacement of model artifacts in S3 with a specially crafted pickle...

CVE-2026-8596

CVE-2026-8596: The ModelBuilder/Serve path in the Amazon SageMaker Python SDK stores the HMAC signing key in cleartext. A remote, authenticated actor with SageMaker describe API permissions and S3 write access to the model artifact path could extract the key from API responses and forge integrity...

PYSEC-2026-40

Diffusers is the a library for pretrained diffusion models. Prior to 0.38.0, a trustremotecode bypass in DiffusionPipeline.frompretrained allows arbitrary remote code execution despite the user passing trustremotecode=False or omitting it, which is the default. The vulnerability has three variant...

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.3

Red Hat Enterprise Linux AI 3.3.3 is now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications...

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.3

Red Hat Enterprise Linux AI 3.3.3 is now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications...

How Dangerous Is Anthropic’s Mythos AI?

Last month, Anthropic made a remarkable announcement about its new model, Claude Mythos Preview: it was so good at finding security vulnerabilities in software that the company would not release it to the general public. Instead, it would only be available to a select group of companies to scan a...

Kimsuky targets organizations with PebbleDash-based tools

Over the past few months, we have conducted an in-depth analysis of specific activity clusters of Kimsuky aka APT43, Ruby Sleet, Black Banshee, Sparkling Pisces, Velvet Chollima, and Springtail, a prolific Korean-speaking threat actor. Our research revealed notable tactical shifts throughout...

PT-2026-41118

Name of the Vulnerable Software and Affected Versions Amazon SageMaker Python SDK versions prior to 2.257.2 Amazon SageMaker Python SDK versions prior to 3.8.0 Description Missing integrity verification in the Triton inference handler allows a remote authenticated actor with S3 write access to th...

MetaBackdoor: Exploiting Positional Encoding As a Backdoor Attack Surface in LLMs

Backdoor attacks pose a serious security threat to large language models LLMs, which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on content-based triggers, requiring explicit modification of the input...

UGen: An Agentic Framework for Generating Microarchitectural Attack PoCs

Microarchitectural attacks continue to evolve, uncovering new exploitation vectors in modern processors. From a defensive perspective, assessing a system's susceptibility to such attacks remains challenging. Developing functional attack implementations is labor-intensive, requires deep...

Detecting Privilege Escalation in Polyglot Microservices Via Agentic Program Analysis

Microservices are widely adopted in modern cloud systems due to their scalability and fault tolerance. However, microservice architectures introduce significant complexity in privilege and permission control, creating risks of privilege escalation where attackers can gain unauthorized access to...

Exploiting LLM Agent Supply Chains Via Payload-Less Skills

Autonomous agents powered by Large Language Models LLMs acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for systematic security evaluation. Current auditing mechanisms a...

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in...

ELECOM多款产品 跨站脚本漏洞

ELECOM WAB-MAT, among others, are products of the ELECOM company. ELECOM WAB-MAT is a management tool for enterprise access points. ELECOM WAB represents a series of wireless access points. ELECOM WAB-S300 is a wireless access point. Several ELECOM products have cross-site scripting...

Backdoor Threats in Variational Quantum Circuits: Taxonomy, Attacks, and Defenses

Variational quantum algorithms VQAs are a central paradigm for noisy intermediate-scale NISQ quantum computing, yet their reliance on predesigned and pretrained variational quantum circuits VQCs introduces critical security vulnerabilities, particularly backdoor attacks. These attacks embed hidde...

ELECOM WRC 操作系统命令注入漏洞

ELECOM WRC is a home-use network camera produced by the Japanese company ELECOM. The ELECOM WRC has a vulnerability related to OS command injection. This vulnerability stems from an OS command injection flaw during the processing of the pingipaddr parameter, which may allow arbitrary OS commands ...

Identifying AI Web Scrapers Using Canary Tokens

From pre-training to query-time augmentation, web-scraped data helps to improve the quality and contextual relevancy of content generated by large language models LLMs. However, large-scale web scraping to feed LLMs can affect site stability and raise legal, privacy, or ethics concerns. If websit...

The vulnerability of the vLLM library for working with large language models involves uncontrolled resource consumption, allowing attackers to trigger a service failure.

The vulnerability of the vLLM library for working with large language models is related to an uncontrolled resource consumption. Exploiting this vulnerability could allow a malicious actor to cause service failures by sending specially crafted HTTP requests...

CVE-2026-44223

vLLM contains a vulnerability (CVE-2026-44223) where the extract_hidden_states speculative decoding pathway can crash the EngineCore process if any request uses penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). The issue arises from an incorrect tensor shape after t...