DREAM: Dynamic Red-Teaming across Environments for AI Models

Large Language Models LLMs are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static, single-turn assessments that miss vulnerabilities from adaptive,...

Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model LLM-based systems. We present an efficient and systematically evaluated defense architecture that mitigates these threats through a lightweight, multi-stage pipeline. Its core component is a...

MAD-OOD: A Deep Learning Cluster-Driven Framework for an Out-Of-Distribution Malware Detection and Classification

Out of distribution OOD detection remains a critical challenge in malware classification due to the substantial intra family variability introduced by polymorphic and metamorphic malware variants. Most existing deep learning based malware detectors rely on closed world assumptions and fail to...

GhostPoster Malware Found in 17 Firefox Add-ons with 50,000+ Downloads

A new campaign named GhostPoster has leveraged logo files associated with 17 Mozilla Firefox browser add-ons to embed malicious JavaScript code designed to hijack affiliate links, inject tracking code, and commit click and ad fraud. The extensions have been collectively downloaded over 50,000...

PentestEval: Benchmarking LLM-Based Penetration Testing with Modular and Stage-Level Design

Penetration testing is essential for assessing and strengthening system security against real-world threats, yet traditional workflows remain highly manual, expertise-intensive, and difficult to scale. Although recent advances in Large Language Models LLMs offer promising opportunities for...

Phantom Stealer Spread by ISO Phishing Emails Hitting Russian Finance Sector

Cybersecurity researchers have disclosed details of an active phishing campaign that's targeting a wide range of sectors in Russia with phishing emails that deliver Phantom Stealer via malicious ISO optical disc images. The activity, codenamed Operation MoneyMount-ISO by Seqrite Labs, has primari...

From Obfuscated to Obvious: A Comprehensive JavaScript Deobfuscation Tool for Security Analysis

JavaScript's widespread adoption has made it an attractive target for malicious attackers who employ sophisticated obfuscation techniques to conceal harmful code. Current deobfuscation tools suffer from critical limitations that severely restrict their practical effectiveness. Existing tools...

mcp-exploit-demo-master

!Imagehttps://github.com/user-attachments/assets/2180e098-091...

CVE-2025-13320

The WP User Manager plugin for WordPress is vulnerable to Arbitrary File Deletion in all versions up to, and including, 2.9.12. This is due to insufficient validation of user-supplied file paths in the profile update functionality combined with improper handling of array inputs by PHP's filterinp...

EUVD-2024-55352

PCMan FTP Server 2.0 contains a buffer overflow vulnerability in the 'pwd' command that allows remote attackers to execute arbitrary code. Attackers can send a specially crafted payload during the FTP login process to overwrite memory and potentially gain system access...

Fake OSINT and GPT Utility GitHub Repos Spread PyStoreRAT Malware Payloads

Cybersecurity researchers are calling attention to a new campaign that's leveraging GitHub-hosted Python repositories to distribute a previously undocumented JavaScript-based Remote Access Trojan RAT dubbed PyStoreRAT. "These repositories, often themed as development utilities or OSINT tools,...

CVE-2025-13320 WP User Manager <= 2.9.12 - Authenticated (Subscriber+) Arbitrary File Deletion via 'current_user_avatar' Parameter

The WP User Manager plugin for WordPress is vulnerable to Arbitrary File Deletion in all versions up to, and including, 2.9.12. This is due to insufficient validation of user-supplied file paths in the profile update functionality combined with improper handling of array inputs by PHP's filterinp...

CVE-2025-13320

CVE-2025-13320 : WP User Manager for WordPress is vulnerable to Authenticated Arbitrary File Deletion via the current_user_avatar parameter in profile updates. The issue arises from insufficient validation of user-supplied file paths and improper handling of array inputs in PHP, enabling attacker...

CVE-2025-13320 WP User Manager <= 2.9.12 - Authenticated (Subscriber+) Arbitrary File Deletion via 'current_user_avatar' Parameter

The WP User Manager plugin for WordPress is vulnerable to Arbitrary File Deletion in all versions up to, and including, 2.9.12. This is due to insufficient validation of user-supplied file paths in the profile update functionality combined with improper handling of array inputs by PHP's filterinp...

Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs

Backdoor attacks embed malicious behaviors into Large Language Models LLMs, enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of the implanted backdoors under user-driven post-deployment continual fine-tuning has been rarely examined. Most prior...

Malicious code in yzip (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 81477965a8a70d1ffef0d388478d3e05ef2eea54ade0a9c00ef923deb41b00cf During initialization of the archive-support class, the package starts code from another file and downloads multi-stage malware --- Category: MALICIOUS - The...

MAL-2025-192468 Malicious code in yzip (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 81477965a8a70d1ffef0d388478d3e05ef2eea54ade0a9c00ef923deb41b00cf During initialization of the archive-support class, the package starts code from another file and downloads multi-stage malware --- Category: MALICIOUS - The...

MAL-2025-192467 Malicious code in gxzip (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 8e0dd8700d5267b8d9bbe270798b11d2250761decf1de89249eab6d90a29080c During initialization of the archive-support class, the package starts code from another file and downloads multi-stage malware --- Category: MALICIOUS - The...

Malicious code in kzip (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 7a81e0fa699edbad810083efb9de4e22f5088c31c22fdf71f7e519269dc5ad01 During initialization of the archive-support class, the package starts code from another file and downloads multi-stage malware --- Category: MALICIOUS - The...

Defining Cost Function of Steganography with Large Language Models

In this paper, we make the first attempt towards defining cost function of steganography with large language models LLMs, which is totally different from previous works that rely heavily on expert knowledge or require large-scale datasets for cost learning. To achieve this goal, a two-stage...