Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates...

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the securit...

LLM-Enabled Applications Require System-Level Threat Monitoring

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges and significantly expands the security attack surface, du...

On the Variability of Source Code in Maven Package Rebuilds

Rebuilding packages from open source is a common practice to improve the security of software supply chains, and is now done at an industrial scale. The basic principle is to acquire the source code used to build a package published in a repository such as Maven Central for Java, rebuild the...

Red-Teaming Claude Opus and ChatGPT-Based Security Advisors for Trusted Execution Environments

Trusted Execution Environments TEEs e.g., Intel SGX and ArmTrustZone aim to protect sensitive computation from a compromised operating system, yet real deployments remain vulnerable to microarchitectural leakage, side-channel attacks, and fault injection. In parallel, security teams increasingly...

Detecting Cybersecurity Threats by Integrating Explainable AI with SHAP Interpretability and Strategic Data Sampling

The critical need for transparent and trustworthy machine learning in cybersecurity operations drives the development of this integrated Explainable AI XAI framework. Our methodology addresses three fundamental challenges in deploying AI for threat detection: handling massive datasets through...

FuzzySQL: Uncovering Hidden Vulnerabilities in DBMS Special Features with LLM-Driven Fuzzing

Traditional database fuzzing techniques primarily focus on syntactic correctness and general SQL structures, leaving critical yet obscure DBMS features, such as system-level modes e.g., GTID, programmatic constructs e.g., PROCEDURE, advanced process commands e.g., KILL, largely underexplored...

Evaluating the Reliability of Digital Forensic Evidence Discovered by Large Language Model: A Case Study

The growing reliance on AI-identified digital evidence raises significant concerns about its reliability, particularly as large language models LLMs are increasingly integrated into forensic investigations. This paper proposes a structured framework that automates forensic artifact extraction,...

LLM Scalability Risk for Agentic-AI and Model Supply Chain Security

Large Language Models LLMs & Generative AI are transforming cybersecurity, enabling both advanced defenses and new attacks. Organizations now use LLMs for threat detection, code review, and DevSecOps automation, while adversaries leverage them to produce malwares and run targeted social-engineeri...

Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection

Mixture-of-Experts MoE offers flexible graph reasoning by combining multiple views of a graph through a learned router. We investigate routing-aware explanations for MoE graph models in malware detection using control flow graphs CFGs. Our architecture builds diversity at two levels. At the node...

Influence of Autoencoder Latent Space on Classifying IoT CoAP Attacks

The Internet of Things IoT presents a unique cybersecurity challenge due to its vast network of interconnected, resource-constrained devices. These vulnerabilities not only threaten data integrity but also the overall functionality of IoT systems. This study addresses these challenges by explorin...

Advanced BLE Scanner with RPA Resolution for Flipper Zero

This project implements a high-performance Bluetooth Low Energy BLE scanner on Flipper Zero, supporting all BLE versions from 4.0 to 5.3. It can discover nearby devices, track specific devices by MAC address, and resolve privacy-randomized Resolvable Private Addresses RPA using Identity Resolving...

Apache Traffic Server Host Header Stability Scanner

This is a safe verification tool designed to detect abnormal Host header handling behavior in Apache Traffic Server without triggering denial of service conditions. The tool performs controlled HTTP requests and analyzes response stability, connection behavior, and service continuity...

Drawing the LINE: Cryptographic Analysis and Security Improvements for the LINE E2EE Protocol

LINE has emerged as one of the most popular communication platforms in many East Asian countries, including Thailand and Japan, with millions of active users. Therefore, it is essential to understand its security guarantees. In this work, we present the first provable security analysis of the LIN...

Radware 2026 Global Threat Analysis Report

This is the Radware 2026 Global Threat Analysis Report that provides details on global network and application attack trends of 2025...

Increase in Malware Enabled ATM Jackpotting Incidents across United States

The Federal Bureau of Investigation FBI is releasing this FLASH to disseminate indicators of compromise IOCs and technical details associated with malware enabled ATM jackpotting. Threat actors exploit physical and software vulnerabilities in ATMs and deploy malware to dispense cash without a...

Windows Registry Active Setup Persistence

This Metasploit module will register a payload to run via the Active Setup mechanism in Windows. Active Setup is a Windows feature that runs once per user at login. It triggers in a user context, losing privileges from admin to user...

AndroWasm: An Empirical Study on Android Malware Obfuscation through WebAssembly

In recent years, stealthy Android malware has increasingly adopted sophisticated techniques to bypass automatic detection mechanisms and harden manual analysis. Adversaries typically rely on obfuscation, anti-repacking, steganography, poisoning, and evasion techniques to AI-based tools, and...

Orbital Escalation: Modeling Satellite Ransomware Attacks Using Game Theory

Ransomware has yet to reach orbit, but the conditions for such an attack already exist. This paper presents the first game-theoretic framework for modeling ransomware against satellites: the orbital escalation game. In this model, the attacker escalates ransom demands across orbital passes, while...

Detecting PowerShell-Based Fileless Cryptojacking Attacks Using Machine Learning

With the emergence of remote code execution RCE vulnerabilities in ubiquitous libraries and advanced social engineering techniques, threat actors have started conducting widespread fileless cryptojacking attacks. These attacks have become effective with stealthy techniques based on PowerShell-bas...

Many Tools, Few Exploitable Vulnerabilities: A Survey of 246 Static Code Analyzers for Security

Static security analysis is a widely used technique for detecting software vulnerabilities across a wide range of weaknesses, application domains, and programming languages. While prior work surveyed static analyzes for specific weaknesses or application domains, no overview of the entire securit...

Advanced BLE Scanner with RPA / IRK Tracking

A Bluetooth Low Energy BLE scanner for Flipper Zero that supports Resolvable Private Address RPA resolution. It discovers nearby BLE devices, tracks each device by MAC address, logs signal strength RSSI history, device name, first/last seen timestamps, and packet count. The scanner features a...

PayPal February 2026 Notice of Data Breach

PayPal has released this notice of data breach to its customers following a data exposure issue that spanned from July 1, 2025 to December 13, 2025...

Automatic, Expressive, and Scalable Fuzzing with Stitching

Fuzzing is a powerful technique for finding bugs in software libraries, but scaling it remains difficult. Automated harness generation commits to fixed API sequences at synthesis time, limiting the behaviors each harness can test. Approaches that instead explore new sequences dynamically lack the...

Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning

Capture-the-Flag CTF competitions serve as gateways into offensive cybersecurity, yet they often present steep barriers for novices due to complex toolchains and opaque workflows. Recently, agentic AI frameworks for cybersecurity promise to lower these barriers by automating and coordinating...

Python Safe TAR Scanner

This Python tool provides a scanner for TAR archives, designed to detect unsafe or malicious entries before extraction...

SofaWiki 3.9.2 Shell Upload

This is a proof of concept remote shell upload exploit for SofaWiki version 3.9.2 that leverages an issue originally discovered in 2024...

PenTiDef: Enhancing Privacy and Robustness in Decentralized Federated Intrusion Detection Systems against Poisoning Attacks

The increasing deployment of Federated Learning FL in Intrusion Detection Systems IDS introduces new challenges related to data privacy, centralized coordination, and susceptibility to poisoning attacks. While significant research has focused on protecting traditional FL-IDS with centralized...

MultiVer: Zero-Shot Multi-Agent Vulnerability Detection

We present MultiVer, a zero-shot multi-agent system for vulnerability detection that achieves state-of-the-art recall without fine-tuning. A four-agent ensemble security, correctness, performance, style with union voting achieves 82.7% recall on PyVul, exceeding fine-tuned GPT-3.5 81.3% by 1.4...

SigInt-Cirtanus 1.0

SigInt-Cirtanus is a Python-based, multi-threaded threat intelligence automation framework designed for defensive cybersecurity operations. It retrieves and processes real-time threat feeds e.g., from URLhaus, validates indicators, and dynamically generates detection artifacts for integration wit...

The CTI Echo Chamber: Fragmentation, Overlap, and Vendor Specificity in Twenty Years of Cyber Threat Reporting

Despite the high volume of open-source Cyber Threat Intelligence CTI, our understanding of long-term threat actor-victim dynamics remains fragmented due to the lack of structured datasets and inconsistent reporting standards. In this paper, we present a large-scale automated analysis of open-sour...

Trojan Horses in Recruiting: A Red-Teaming Case Study on Indirect Prompt Injection in Standard Vs. Reasoning Models

As Large Language Models LLMs are increasingly integrated into automated decision-making pipelines, specifically within Human Resources HR, the security implications of Indirect Prompt Injection IPI become critical. While a prevailing hypothesis posits that "Reasoning" or "Chain-of-Thought" Model...

SmarterMail 16.3.6989.16341 Path Traversal

This PHP proof of concept is a detection-only artifact generator for CVE-2025-52691 affecting SmarterMail version 16.3.6989.16341. It sends a crafted multipart upload request to the /api/upload endpoint, leveraging a path traversal condition in the contextData GUID to determine whether the target...

Comparison of Security Mechanisms of Mathematical Cipher, Wyner Scheme, QKD, and Quantum Stream Cipher

A new generation of global communications technology has been emerging. These systems, which utilize established device technologies and quantum effect devices, require ultra-high speeds, low cost, and strong security. In recent years, global communication systems have faced various practical...

TFL: Targeted Bit-Flip Attack on Large Language Model

Large language models LLMs are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks BFAs, which exploit computer main memory i.e., DRAM vulnerabilitie...

What Makes a Good LLM Agent for Real-World Penetration Testing?

LLM-based agents show promise for automating penetration testing, yet reported performance varies widely across systems and benchmarks. We analyze 28 LLM-based penetration testing systems and evaluate five representative implementations across three benchmarks of increasing complexity. Our analys...

Windows Registry Persistence Via Userinit

This Metasploit module will install a payload that is executed during user logon. It writes a payload executable to disk and modifies the Userinit registry value in "HKLM\Software\Microsoft\Windows NT\CurrentVersion\Winlogon" to append the payload path, causing it to execute when any user logs in...

Discovering Universal Activation Directions for PII Leakage in Language Models

Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information PII leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability framework that...

Mind the Gap: Evaluating LLMs for High-Level Malicious Package Detection Vs. Fine-Grained Indicator Identification

The prevalence of malicious packages in open-source repositories, such as PyPI, poses a critical threat to the software supply chain. While Large Language Models LLMs have emerged as a promising tool for automated security tasks, their effectiveness in detecting malicious packages and indicators...

Automating Agent Hijacking Via Structural Template Injection

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model LLM ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on manually crafted, semantics-driven prompt manipulation, which...

Aether Smart Contract Security Analysis Framework 4.7.1

Aether is a Python-based framework for analyzing Solidity smart contracts, generating vulnerability findings, producing Foundry-based proof-of-concept PoC tests, and validating exploits on mainnet forks. It combines Solidity AST parsing, taint analysis, control flow graph analysis, cross-contract...

btrpa-scan BLE Scanner

btrpa-scan is a Bluetooth Low Energy BLE scanner with advanced Resolvable Private Address RPA resolution. Discover nearby BLE devices, track a specific device by MAC address, or resolve privacy-randomized addresses using an Identity Resolving Key IRK...

Arc2Morph: Identity-Preserving Facial Morphing with Arc2Face

Face morphing attacks are widely recognized as one of the most challenging threats to face recognition systems used in electronic identity documents. These attacks exploit a critical vulnerability in passport enrollment procedures adopted by many countries, where the facial image is often acquire...

Regular Expression Denial of Service (ReDoS) Detector

This Metasploit auxiliary module implements a scientific approach to detecting and validating ReDoS vulnerabilities in HTTP-based applications. It leverages context-aware payload generation, length progression testing, and statistical analysis to identify inefficient regular expressions that may...

Recursive Language Models for Jailbreak Detection: A Procedural Defense for Tool-Augmented Agents

Jailbreak prompts are a practical and evolving threat to large language models LLMs, particularly in agentic systems that execute tools over untrusted content. Many attacks exploit long-context hiding, semantic camouflage, and lightweight obfuscations that can evade single-pass guardrails. We...

mailcow: Dockerized Host Header Password Reset Poisoning Scanner

This Metasploit module adds a scanner for a Host header poisoning vulnerability in mailcow:dockerized versions prior to 2025-01a. The vulnerability occurs because the application improperly trusts the HTTP Host header when generating password reset links. By supplying a crafted Host header during...

Collaborative Zone-Adaptive Zero-Day Intrusion Detection for IoBT

The Internet of Battlefield Things IoBT relies on heterogeneous, bandwidth-constrained, and intermittently connected tactical networks that face rapidly evolving cyber threats. In this setting, intrusion detection cannot depend on continuous central collection of raw traffic due to disrupted link...

Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses against LLM Code Analysis

AI-assisted code review is widely used to detect vulnerabilities before production release. Prior work shows that adversarial prompt manipulation can degrade large language model LLM performance in code generation. We test whether similar comment-based manipulation misleads LLMs during...

DARTH-PUM: A Hybrid Processing-Using-Memory Architecture

Analog processing-using-memory PUM; a.k.a. in-memory computing makes use of electrical interactions inside memory arrays to perform bulk matrix-vector multiplication MVM operations. However, many popular matrix-based kernels need to execute non-MVM operations, which analog PUM cannot directly...

Bluetooth RFCOMM 1.1 Signal-Triggered Air-Gap Interaction

This project demonstrates how Flipper Zero can be used to interact with devices in an Air-Gap context using Bluetooth RFCOMM signals. The system monitors RSSI signal strength and uses statistical peak detection Z-Score analysis to identify significant signal spikes from target devices. When a pea...