Experimental Evaluation of Security Attacks on Self-Driving Car Platforms

Deep learning-based perception pipelines in autonomous ground vehicles are vulnerable to both adversarial manipulation and network-layer disruption. We present a systematic, on-hardware experimental evaluation of five attack classes: FGSM, PGD, man-in-the-middle MitM, denial-of-service DoS, and...

Microsoft Windows Service Binary Misconfiguration Tester

This document and included Metasploit module analyze the security risks associated with improper Windows service configurations, specifically focusing on writable service binary paths that may lead to privilege escalation. Note that this condition does not occur on a default Windows installation...

OpenSSL Security Advisory 20260313

OpenSSL Security Advisory 20260313 - An OpenSSL TLS 1.3 server may fail to negotiate the expected preferred key exchange group when its key exchange group configuration includes the default by using the "DEFAULT" keyword...

Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents

OpenClaw-like agents offer substantial productivity benefits, yet they are insecure by default because they combine untrusted inputs, autonomous action, extensibility, and privileged system access within a single execution loop. We use OpenClaw as an exemplar of a broader class of agents that...

Apple Security Advisory 03-11-2026-1

Apple Security Advisory 03-11-2026-1 - iOS 16.7.15 and iPadOS 16.7.15 addresses memory corruption issues...

Microsoft Windows Malicious Script File Generator

This PHP script generates a malicious .WSF Windows Script File containing both VBScript and JScript payload blocks. The payload runs arbitrary system commands through WScript.Shell...

Windows File Explorer NTLM Forced Authentication Hash Disclosure 1.0

Windows File Explorer contains persistent forced authentication behavior that automatically transmits NTLM challenge-response hashes to remote SMB/WebDAV endpoints during routine file operations, enabling credential theft and potential domain compromise through NTLM relay attacks. This is not an...

Graph Neural Network-Based DDoS Protection for Data Center Infrastructure

In light of rising cybersecurity threats, data center providers face growing pressure to protect their own management infrastructure from Distributed Denial-of-Service DDoS attacks. While tenant-managed cages generally fall outside the data center's direct security purview, a successful DDoS...

Apple Security Advisory 03-11-2026-2

Apple Security Advisory 03-11-2026-2 - iOS 15.8.7 and iPadOS 15.8.7 addresses code execution and use-after-free vulnerabilities...

WebGPU Resource Isolation Auditor

This WebGPU security javascript confirms that memory isolation between buffers is fully enforced. It does not exploit any vulnerability but rather demonstrates that behavior is working as expected. It validates that attempts to read or write outside of Buffer A's bounds are safely handled by eith...

Ransomware and Artificial Intelligence: A Comprehensive Systematic Review of Reviews

This study provides a comprehensive synthesis of Artificial Intelligence AI, especially Machine Learning ML and Deep Learning DL, in ransomware defense. Using a "review of reviews" methodology based on PRISMA, this paper gathers insights on how AI is transforming ransomware detection, prevention,...

Microsoft Windows Image File Execution Options (IFEO) Persistence

This PHP script leverages legitimate Windows debugging features to establish persistent remote access. This technique leverages the Image File Execution Options IFEO registry keys to configure a monitor process that automatically executes when a specified target process exits. Windows allows...

Quantum CDMA-Based Continuous Variable Quantum Key Distribution Using Chaotic Phase Shifters

We present a quantum code-division multiple-access q-CDMA framework for multiuser continuous-variable quantum key distribution CV-QKD over a shared quantum channel. The proposed architecture employs chaotic phase shifters to encode and decode quantum states, enabling efficient multiplexing and...

American Fuzzy Lop plus plus 4.40c

Google's American Fuzzy Lop is a brute-force fuzzer coupled with an exceedingly simple but rock-solid instrumentation-guided genetic algorithm. afl++ is a superior fork to Google's afl. It has more speed, more and better mutations, more and better instrumentation, custom module support, etc...

Microsoft Windows Registry Editor Version 5.00 Malicious Registry File Generator

This script generates a malicious Windows Registration Entries .reg file designed to establish persistence on Windows systems. It creates a registry file that, when executed by a user, adds the attacker's payload to Windows auto-run registry keys. Written in PHP...

FoSAM: Forward Secret Messaging in Ad-Hoc Networks

Apps such as Firechat and Bridgefy have been used during recent protests in Hong Kong and Iran, as they allow communication over ad-hoc wireless networks even when internet access is restricted. However, these apps do not provide sufficient protection as they do not achieve forward secrecy in...

ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents

Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, because data produced by one tool can be persisted and later reused as input to another tool, enabling exploitable source-to-sink dataflows that only...

Automatic Attack Script Generation: A MDA Approach

It is widely recognized that practical exercises are crucial for teaching cybersecurity in higher education. However, their setup is not only expensive, time-consuming, and prone to numerous errors, but also requires technical and programming skills to create attack contexts and scripts. To...

Agent Privilege Separation in OpenClaw: A Structural Defense against Prompt Injection

Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark Greshake et al., 2024 against current generation models running inside OpenClaw, an open source multitool agent platform. Our proposed defense...

nah Claude Code Tool

Claude Code's permission system is allow-or-deny per tool, but that doesn't really scale. Deleting some files is fine sometimes. And git checkout is sometimes catastrophic. Even when you curate permissions, 200 IQ Opus can find a way around it. Maintaining a deny list is a fool’s errand. What's...

Highly Autonomous Cyber-Capable Agents: Anticipating Capabilities, Tactics, and Strategic Implications

This report introduces the concept of "Highly Autonomous Cyber-Capable Agents" HACCAs, AI systems capable of autonomously conducting multi-stage cyber campaigns at a level comparable to today's top criminal hacking groups or state-affiliated threat actors, and analyzes the security implications o...

RadEar: A Self-Supervised RF Backscatter System for Voice Eavesdropping and Separation

Eavesdropping on voice conversations presents a growing threat to personal privacy and information security. In this paper, we present RadEar, a novel RF backscatter-based system designed to enable covert voice eavesdropping through walls. RadEar consists of two key components: i a batteryless RF...

Systematic Security Analysis of the Iridium Satellite Radio Link

The Iridium Low Earth Orbit LEO satellite constellation remains a unique provider of global communications for critical industries, governments, and private users, serving over 2.5 million active subscribers despite recent market competition. In contrast to terrestrial wireless standards such as...

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats

Autonomous Large Language Model LLM agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege execution capabilities substantially expand the system attack...

Internet-Scale Measurement of React2Shell Exploitation Using an Active Network Telescope

The increasing adoption of server-side component-based web frameworks has introduced new application-layer attack surfaces that remain insufficiently understood at Internet scale. On 3 December 2025, a critical remote code execution vulnerability CVE-2025-55182 in React Server Components, referre...

Microsoft Windows Service Installation Persistence

This Metasploit module creates a persistent Windows service using multiple methods. It supports PowerShell, SC.exe, and WMI methods for service creation...

Phrack 73 Call for Papers

Phrack has announced their Call For Papers for Phrack issue 73. If you do cutting edge security research, you should write for Phrack. It is widely regarded as an unparalleled resource in the security community...

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic...

Microsoft Windows 11 Build 26200 File Explorer Auditor

This Metasploit module provides a defensive pre-execution assessment for the Windows vulnerability where File Explorer fails to properly restrict access to sensitive system locations...

OpenClaw PRISM: A Zero-Fork, Defense-In-Depth Runtime Security Layer for Tool-Augmented LLM Agents

Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We present OpenClaw PRISM, a zero-fork runtime security layer...

Keys on Doormats: Exposed API Credentials on the Web

Application programming interfaces APIs have become a central part of the modern IT environment, allowing developers to enrich the functionality of applications and interact with third parties such as cloud and payment providers. This interaction often occurs through authentication mechanisms tha...

Microsoft Windows Active Setup Persistence Module

This Metasploit module leverages the Windows Active Setup mechanism to establish persistence while integrating multiple evasion and stealth techniques designed to reduce forensic visibility and bypass detection mechanisms...

Microsoft Windows Service Installation Persistence

This is a Microsoft Windows persistent service installer for creating backdoor services that automatically start payloads upon system boot. This tool is designed for authorized penetration testing and security research purposes. This variant from the author is written in PHP...

On the Possible Detectability of Image-In-Image Steganography

This paper investigates the detectability of popular imagein-image steganography schemes 1, 2, 3, 4, 5. In this paradigm, the payload is usually an image of the same size as the Cover image, leading to very high embedding rates. We first show that the embedding yields a mixing process that is...

Microsoft Windows 11 24H2 NTLM Relay Orchestrator Privilege Escalation

This Metasploit module checks the SMB Signing status on remote targets. If signing is not required, the target is vulnerable to NTLM Relay attacks. It serves as an automated pre-flight check for relay operations...

AEGIS: No Tool Call Left Unchecked -- a Pre-Execution Firewall and Audit Layer for AI Agents

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer with no framework-agnostic control point in between...

FP-Predictor - False Positive Prediction for Static Analysis Reports

Static Application Security Testing SAST tools play a vital role in modern software development by automatically detecting potential vulnerabilities in source code. However, their effectiveness is often limited by a high rate of false positives, which wastes developer's effort and undermines trus...

LROO Rug Pull Detector: A Leakage-Resistant Framework Based on On-Chain and OSINT Signals

Smart contract-based ecosystems enable decentralized applications without trusted intermediaries, but their immutability and permissionless design also facilitate large-scale fraud. One of the most prevalent attacks is the rug pull, where project operators abruptly withdraw liquidity after...

TOSSS: A CVE-Based Software Security Benchmark for Large Language Models

With their increasing capabilities, Large Language Models LLMs are now used across many industries. They have become useful tools for software engineers and support a wide range of development tasks. As LLMs are increasingly used in software development workflows, a critical question arises: are...

QuaNTUM: A Modular Quantum Communication Testbed for Scalable Fiber and Satellite Integration

Secure communication is essential for modern society, from financial transactions to critical infrastructure. As classical encryption faces threats from advancing computational power, quantum communication provides a fundamentally secure alternative based on physical laws. We present QuaNTUM...

Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw

Code agents powered by large language models can execute shell commands on behalf of users, introducing severe security vulnerabilities. This paper presents a two-phase security analysis of the OpenClaw platform. As an open-source AI agent framework that operates locally, OpenClaw can be integrat...

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services

The rapid adoption of large language models LLMs in financial services introduces new operational, regulatory, and security risks. Yet most red-teaming benchmarks remain domain-agnostic and fail to capture failure modes specific to regulated BFSI settings, where harmful behavior can be elicited...

Silent Subversion: Sensor Spoofing Attacks Via Supply Chain Implants in Satellite Systems

Spoofing attacks are among the most destructive cyber threats to terrestrial systems, and they become even more dangerous in space, where satellites cannot be easily serviced, and operators depend on accurate telemetry to ensure mission success. When telemetry is compromised, entire spaceborne...

Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks

Adversarial examples can represent a serious threat to machine learning ML algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems NIDS, they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS...

The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey

AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex security challenges fundamentally different from those in...

Layered Performance Analysis of TLS 1.3 Handshakes: Classical, Hybrid, and Pure Post-Quantum Key Exchange

In this paper, we present a laboratory study focused on the impact of post-quantum cryptography PQC algorithms on multiple layers of stateful HTTP over TLS transactions: the TCP handshake, the intermediate TCP-TLS layer, the TLS handshake, the intermediate TLS layer, and the HTTP application laye...

SharePoint / OneDrive Explorer via Microsoft Graph API

The SharePoint / OneDrive Explorer is a Metasploit Auxiliary module designed to interact with Microsoft Graph API in order to explore and retrieve information from Microsoft SharePoint and Microsoft OneDrive environments. The module authenticates using OAuth2 Client Credentials with a Tenant ID,...

Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law framework for jailbreaks by treating each attack as a...

Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles toward suboptimal routes and increase congestion. To addres...

Human Presence Detection Via Wi-Fi Range-Filtered Doppler Spectrum on Commodity Laptops

Human Presence Detection HPD is key to enable intelligent power management and security features in everyday devices. In this paper we propose the first HPD solution that leverages monostatic Wi-Fi sensing and detects user position using only the built-in Wi-Fi hardware of a device, with no need...