Toward Cryptographically Verifiable Authorization for Autonomous AI Agents: A Security Hypothesis, Preliminary Formal Model, and Proof-Of-Concept Implementation

Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight. Existing authentication and authorization mechanisms establish identity and delegate authority, but do not inherently provide cryptographic evidence that a concrete...

Synology Man-In-The-Middle

Synology stale DNS allows practical interception of traffic from vulnerable DSM clients, making older vulnerabilities more practical to exploit...

Safety and Security: Experimental Validation of Encrypted Model Predictive Control

In this paper, we revisit the problem of an encrypted model predictive control MPC design, representing a significant challenge in the recent field of secure process control. Existing methods in secure optimization-based control are non-existent and even partial implementation fails to address th...

What AI Red-Team Evaluations Can and Cannot Prove

Red-team evaluations of AI models support some claims and not others, and the boundary between the two is calculable rather than merely a matter of judgment. We define the evidential ceiling of an evaluation as the largest factor by which one result can move belief under a fixed testing budget,...

From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python

The original ALPHA benchmark introduced a taxonomy-aware penalty for evaluating CWE-level vulnerability prediction in Python and proposed that the penalty could theoretically also serve as a training signal. This paper provides that validation. We compare three delivery mechanisms: supervised...

ManageEngine AD360 Detection Tool

A proof of concept detection tool for ManageEngine AD360 products affected by CVE-2026-11374. The Python utility safely checks whether an ADSelfService Plus, RecoveryManager Plus, M365 Manager Plus, or ADAudit Plus deployment is AD360-integrated and therefore meets the exploit precondition for th...

Directed Symbolic Execution for Vulnerability Discovery: An LLM-Guided Approach in KLEE

Symbolic execution effectively discovers security violations but suffers from path explosion. Engines like KLEE therefore use path prioritization heuristics to order state exploration, typically optimizing code coverage. However, path prioritization can become trapped in cyclic control-flow...

ToolGuardian: Declarative Security for AI Agent-Tool Interactions

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy...

DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection

Most existing LLM safety evaluation and defense methods follow a static formulation: jailbreak vulnerabilities are evaluated with fixed attack methods, and guardrails are trained on fixed malicious prompt datasets. However, real-world adversaries continuously evolve their capabilities and expand...

OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills

LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent safety risks that only emerge during actual execution. In this work, we...

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to...

Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection

An increase in advanced Android malware requires the use of deep learning models, which can run on Android devices. But there is a trade-off between security and energy use, as strong detection models can drain the battery of devices fast. This work tests different Multi-Layer Perceptron MLP mode...

A Covert Precision Satellite Communication Framework Assisted by Cooperative IRSs

Satellite communication SatCom, as an effective complement to terrestrial networks, has attracted considerable attention from both academia and industry owing to its wide coverage and high flexibility. However, the inherent openness of satellite links renders them highly vulnerable to...

Two-Way Wiretap Channel under Mixed Secrecy Constraint

This paper studies the two-way wiretap channel TW-WC with an external eavesdropper under strong one-sided mixed secrecy: only User1's message is required to be secure from the eavesdropper, while no secrecy constraint is imposed on User2's message. Secrecy is measured by the information leakage o...

Xalgorix Autonomous AI Pentesting Agent 4.5.71

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

Defense against LLM Backdoors Using Critical Neuron Isolation Pruning

Large language models LLMs are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations. First, they focus on fine-tuning-based backdoors e.g., PEFT...

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models LLMs demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight...

Logwatch 7.15

Logwatch analyzes and reports on unix system logs. It is a customizable and pluggable log monitoring system which will go through the logs for a given period of time and make a customizable report. It should work right out of the package on most systems...

An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports

Cyber Threat Intelligence CTI reports richly describe real-world attack processes, but their unstructured narratives cannot be directly used for automated attack-path reasoning. Existing CTI extraction methods focus on indicators, entities, or TTP labels without modeling the execution conditions...

Geometric Configurations of Perturbed Jailbreak Prompts

Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat to LLM safety. In this paper, we investigate the internal representations of such string-level perturbed jailbreak inputs in the small weight model...

Construction of a Class of Communication-Efficient Quantum Secret Sharing Schemes

Quantum secret sharing is a fundamental technique in quantum cryptography. However, in practical quantum networks, it still faces several bottlenecks, such as high quantum communication cost and low transmission efficiency. To reduce the communication cost, ramp quantum secret sharing schemes hav...

Qualys Security Advisory - snap-confine Privilege Escalation

Qualys has discovered a local root privilege escalation vulnerability in set-capabilities versions of snap-confine...

HijackKV: New Threat in Position-Independent KV Cache Reuse

Key-Value KV cache reduces inference latency in large language models LLMs. Traditional prefix-based reuse has low cache hit rates across inference requests because it requires exact token and position matches. To improve efficiency, recent system optimizations introduce position-independent KV...

Evaluating Large Language Models for Symbolic Security Protocol Analysis

Security protocol verification relies on formal tools such as ProVerif and OFMC. This study evaluates whether Large Language Models LLMs can perform comparable analysis. We test GPT and DeepSeek in chat and reasoning modes over three runs on 130 obfuscated AnB/AnBx protocols covering 388 security...

Security Vulnerability Patterns in AI-Generated Code: A Cross-Model Comparative Study

LLM-based coding tools enable non-expert users to generate routine automation scripts that may enter enterprise workflows without meaningful security review. This study examines that risk directly. Code was collected from ChatGPT, Microsoft Copilot, and Google Gemini using identical prompts acros...

Enhancing Attack Detection Capabilities in BACnet/IP Networks Using Machine-Learning Models

Building Automation Systems BAS manage critical building functions using protocols such as BACnet/IP, yet defenders have limited tooling and few labeled datasets for detecting BACnet-specific attacks. This work addresses these gaps through three contributions. First, CISA's Zeek BACnet parser is...

Buzz to Boom: Detecting Message Progression Vulnerabilities in Electron Applications Via Segmented Directed Fuzzing

Electron is a popular framework for building cross-platform desktop applications using web technologies. Such applications consist of multiple processes with different privilege levels that communicate via message passing. When inter-process messages carry attacker-controlled inputs, they can...

IssueTrojanBench: Benchmarking AI Coding Agents against Malicious Issue Requests

AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools. Coding agents inherit security risks from both the LLM backbone, where adversarial prompts, poisoned...

Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code

Large language models can generate C code from natural-language descriptions, but resulting programs often contain security vulnerabilities and compilation errors, posing risks for embedded and resource-constrained systems. This work investigates how feedback and retrieval improve reliability of...

Data Leakage Prevention in Agentic Applications Via Preemptive Hardening

Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks. Enforcing required controls consistently is particularly challenging in workflows spanning many...

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA

Large Language Models LLMs are increasingly fine-tuned for critical-domain Question-Answering QA, yet choosing which small model to adapt, before paying the cost of adaptation, remains difficult. Fine-tuning can improve domain alignment, but it may also erode prior knowledge, weaken...

Twin Agent: Context Residual Compression for Privilege Separated Agents

Large language model LLM agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and...

PTSan: A Practical Memory Safety Sanitizer for C/C++ with Pointer-Object Authority

Memory safety errors remain the dominant source of severe vulnerabilities in C and C++. Pointer-based sanitizers provide stronger guarantees than location-based tools such as LLVM's ASan, but their overhead and compatibility limitations have constrained production use. We present PTSan, an LLVM...

Xalgorix Autonomous AI Pentesting Agent 4.5.69

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

Large Language Model LLM agents are increasingly used for coding and terminal automation, making shell-command dispatch a high-stakes runtime control point. We study command-level pre-execution mediation for individual shell commands produced by LLM agents under bounded path context. Existing...

XSSer Penetration Testing Tool 1.9

XSSer is an open source penetration testing tool that automates the process of detecting and exploiting XSS injections against different applications. It contains several options to try to bypass certain filters, and various special techniques of code injection. 12 additions, 12 modifications, 10...

AuthProbe: Specification-Driven, Multi-Identity Detection of Broken Object-Level Authorization in Recruitment API

Broken Object-Level Authorization BOLA, also known as Insecure Direct Object Reference IDOR, has topped the OWASP API Security ranking since 2019 and is the root cause of some of the largest exposures of applicant data in recruitment technology. The defining feature of this flaw class is that a...

Fluxion 6.31

Fluxion is a security auditing and social-engineering research tool. It is a remake of linset by vk496 with hopefully fewer bugs and more functionality. The script attempts to retrieve the WPA/WPA2 key from a target access point by means of a social engineering phishing attack. It's compatible wi...

Investigation of STEEP for Secure Communications over SIMO and MISO Channels Subject to Full-Duplex Jamming and Eavesdropping

Secure communications over SIMO and MISO channels between wireless nodes are commonly encountered in applications and widely considered in the literature. This paper investigates such a problem by considering a newly proposed scheme called secrecy-message transmission by echoing encrypted probes...

Examining User Behavior and Cognitive Biases in Personal Password Security

Despite increasing awareness of cybersecurity risks, users continue to engage in insecure password practices, such as reusing passwords, choosing weak credentials, and neglecting security recommendations. The study explores the behavioral and cognitive factors that influence password...

Exploiting Load/Store Leakage of Sparse Vectors for Key Recovery in HQC

Hamming Quasi-Cyclic HQC is a code-based key encapsulation mechanism selected by NIST for standardization, making its resistance to implementation attacks critically important. We present a side-channel attack that exploits load/store leakage in the manipulation of HQC's sparse secret vectors...

When to Trust the Map: Confidence-Aware LLM Routing for Automotive CVE-To-ATM Mapping

Public CVE descriptions report the technical conditions and impact of vulnerabilities, whereas the Auto-ISAC Automotive Threat Matrix ATM expresses an adversary's tactics and techniques. Because the two representations are not directly aligned, incorrect automated mappings in safety-critical...

GARAGE: Characterizing the Automation Boundary in LLM-Based Attack Graph Generation

While modern vehicle security depends on effective Cyber Threat Intelligence CTI synthesis, current automated tools struggle with unstructured data and automotive-specific architectural nuances. To bridge this gap, we introduce GARAGE, a RAG-powered framework that converts fragmented CTI into an...

Xalgorix Autonomous AI Pentesting Agent 4.5.67

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

Nebula AI-Powered Penetration Testing 2.0.1b2

Nebula is an advanced, AI-powered penetration testing open-source tool that revolutionizes penetration testing by integrating state-of-the-art AI models into your command-line interface. Designed for cybersecurity professionals, ethical hackers, and developers, Nebula automates vulnerability...

WordPress 5.6+ SkelerSecurity Core Security Plugin REST Batch API Mitigation

This WordPress plugin provides a temporary mitigation for the REST Batch API vulnerability chain commonly referred to as "wp2shell." It requires authentication before requests to the /wp-json/batch/v1 and ?restroute=/batch/v1 endpoints are processed, preventing unauthenticated exploitation of the...

Broken Gates: Re-Evaluating Web Bot Defenses in the Age of LLM Agents

LLM-based browser agents are rapidly changing the threat landscape for web security. Unlike traditional automation frameworks that execute predefined scripts, these agents can autonomously navigate websites, reason about page content, and interact with web interfaces using natural-language...

Russian State Actors Are Compromising IP Cameras in Europe for Military Purposes

Intelligence from the Netherlands General Intelligence and Security Service AIVD and the Netherlands Defence Intelligence and Security Service MIVD - the Dutch services - illustrates that Russian state actors are systematically conducting digital espionage operations via IP cameras cameras with...

Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT

Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them. Most reported detection accuracies, however, are measured on clean, in-distribution test data rather than on emails deliberately altered to evade detection. Th...

Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state -- a compromise realized via legitimate OS system call invocation. We refer to this class of threats as self-state attacks. In this paper, we...