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...

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...

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...

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...

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 ...

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...

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...

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...

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...

mamba language model framework vulnerable to insecure deserialization when loading pre-trained models from HuggingFace Hub

The mamba language model framework thru 2.2.6 is vulnerable to insecure deserialization CWE-502 when loading pre-trained models from HuggingFace Hub. The MambaLMHeadModel.frompretrained method uses torch.load to load the pytorchmodel.bin weight file without enabling the security-restrictive...

Ludwig framework is vulnerable to insecure deserialization in its model serving component

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

GHSA-PQ2F-X424-6FJM mamba language model framework vulnerable to insecure deserialization when loading pre-trained models from HuggingFace Hub

The mamba language model framework thru 2.2.6 is vulnerable to insecure deserialization CWE-502 when loading pre-trained models from HuggingFace Hub. The MambaLMHeadModel.frompretrained method uses torch.load to load the pytorchmodel.bin weight file without enabling the security-restrictive...

CVE-2026-31239

The mamba language model framework thru 2.2.6 is vulnerable to insecure deserialization CWE-502 when loading pre-trained models from HuggingFace Hub. The MambaLMHeadModel.frompretrained method uses torch.load to load the pytorchmodel.bin weight file without enabling the security-restrictive...

EUVD-2025-209779

A vulnerability has been identified in blueplanet 100 NX3 M8 All versions, blueplanet 100 TL3 GEN2 All versions V6.1.4.9, blueplanet 105 TL3 All versions, blueplanet 105 TL3 GEN2 All versions V6.1.4.9, blueplanet 110 TL3 All versions, blueplanet 125 NX3 M11 All versions, blueplanet 125 TL3 All...

CVE-2026-41125

A vulnerability has been identified in blueplanet 100 NX3 M8 All versions, blueplanet 100 TL3 GEN2 All versions, blueplanet 105 TL3 All versions, blueplanet 105 TL3 GEN2 All versions, blueplanet 110 TL3 All versions, blueplanet 125 NX3 M10 All versions, blueplanet 125 TL3 All versions, blueplanet...

CVE-2024-54017

A vulnerability has been identified in SIPROTEC 5 6MD84 CP300 All versions = V7.80 = V7.80 = V7.80 = V7.80 = V7.80 = V7.80, SIPROTEC 5 7SA82 CP150 All versions = V7.80 = V7.80 = V7.80, SIPROTEC 5 7SD82 CP150 All versions = V7.80 = V7.80 = V7.80, SIPROTEC 5 7SJ81 CP150 All versions = V7.80, SIPROT...

PT-2026-39977

Name of the Vulnerable Software and Affected Versions SIPROTEC 5 6MD84 CP300 versions prior to V11.0 SIPROTEC 5 6MD85 CP200 affected versions not specified SIPROTEC 5 6MD85 CP300 versions V7.80 through V11.0 SIPROTEC 5 6MD86 CP200 affected versions not specified SIPROTEC 5 6MD86 CP300 versions...

This Week in Spring - May 12th, 2026

Hi, Spring fans! As I write this I am in Miami, FL at the CodeRemix.ai show, focused on the wide and wonderful world of OpenRewrite and Moderne. I've got a talk to give so let's dive right into it! a quick note about the upcoming release train dates in last week's installment of A Bootiful Podcas...

CVE-2026-31239

The mamba language model framework thru 2.2.6 is vulnerable to insecure deserialization CWE-502 when loading pre-trained models from HuggingFace Hub. The MambaLMHeadModel.frompretrained method uses torch.load to load the pytorchmodel.bin weight file without enabling the security-restrictive...