Do Coding Agents Understand Least-Privilege Authorization?

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority that exposes sensitive surfaces.To study whether current...

OpenAnt: LLM-Powered Vulnerability Discovery through Code Decomposition, Adversarial Verification, and Dynamic Testing

Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approaches such as fuzzing require substantial infrastructure and often target narrow classes of bugs. Recent advances in large language models...

Reasoning As an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

Large Reasoning Models LRMs have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought CoT mechanism introduces new security risks, making them particularly vulnerable to jailbreak...

CHASE: LLM Agents for Dissecting Malicious PyPI Packages

Modern software package registries like PyPI have become critical infrastructure for software development, but are increasingly exploited by threat actors distributing malicious packages with sophisticated multi-stage attack chains. While Large Language Models LLMs offer promising capabilities fo...

WordPress Order Delivery Date Missing Authorization

WordPress Order Delivery Date plugin versions prior to 12.3.1 have missing authorization and cross site request forgery vulnerabilities surrounding the importing of settings...

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious instructions into skills, making them easily detectable b...

MikroTik RouterOS Username Enumeration

MikroTik RouterOS suffers from a username enumeration vulnerability...

Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection

Credential leakage in public source code repositories poses a critical security threat, with over 23.8 million secrets exposed in 2024 alone. Existing detection tools suffer from high false-positive rates because rigid pattern matching and binary classification schemes fail to distinguish genuine...

PickleFuzzer: A Case Study in Fuzzing for Discrepancies between Python Pickle Implementations

Python's native serialization protocol, pickle, is a powerful but insecure format for transferring untrusted data. It is frequently used, especially for saving machine learning models, despite known security challenges. While developers sometimes mitigate this risk by restricting imports during...

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation

Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor attacks remains largely underexplored. Prior segmentation backdoor studies transfer threat settings from existing image classification tasks, focusing...

Sparse Autoencoders Are Capable LLM Jailbreak Mitigators

Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering CC-Delta, an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representations of the same harmful request with and without...

SleepWalk: Exploiting Context Switching and Residual Power for Physical Side-Channel Attacks

Context switching is utilized by operating systems to change the execution context between application programs. It involves saving and restoring the states of multiple registers and performing a pipeline flush to remove any pre-fetched instructions, leading to a higher instantaneous power...

WordPress WPMasterToolKit 1.13.1 Shell Upload

WordPress WPMasterToolKit plugin versions 1.13.1 and below remote shell upload exploit...

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...

Joern 4.0.539

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

ARIstoteles -- Dissecting Apple's Baseband Interface

Wireless chips and interfaces expose a substantial remote attack surface. As of today, most cellular baseband security research is performed on the Android ecosystem, leaving a huge gap on Apple devices. With iOS jailbreaks, last-generation wireless chips become fairly accessible for performance...

Poking around in the Dark: Why a Shared Understanding of Components Matters

By listing the components included in an application, Software Bills of Materials SBOMs are intended to support the timely identification of vulnerable components and ensure the security of the software supply chain. However, we question the underlying assumption that there is agreement on the...

LITE-SOC: Lightweight Security Operations Center Simulator for Cybersecurity Education

This innovative practice WIP paper describes LITE-SOC, a lightweight web-based Security Operations Center SOC simulator designed for instructor-led cybersecurity education. SOC analysts must triage large volumes of alerts, separate genuine threats from false positives, and communicate decisions...

MalwarePT: A Binary-Level Foundation Model for Malware Analysis

Automated malware analysis increasingly relies on machine learning, yet most existing methods remain task-specific and depend on handcrafted features or narrowly scoped models. Recent developments in binary-level foundation models suggest a path toward reusable program representations, but their...

Unvalidated Trust: Cross-Stage Vulnerabilities in Large Language Model Architectures

As Large Language Models LLMs are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust between processing stages become a practical concern. This paper presents a mechanism-centered taxonomy of 41 recurring risk patterns in commercial LLMs...

EchoLeak: the First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Large language model LLM assistants are increasingly integrated into enterprise workflows, raising new security concerns as they bridge internal and external data sources. This paper presents an in-depth case study of EchoLeak CVE-2025-32711, a zero-click prompt injection vulnerability in Microso...

Architectural Backdoors in Deep Learning: a Survey of Vulnerabilities, Detection, and Defense

Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural backdoors evade standard mitigation techniques and persist...

Insights into Security-Related AI-Generated Pull Requests

Recent years have experienced growing contributions of AI coding agents that assist human developers in various software engineering tasks. However, this growing AI-assisted autonomy raises questions about security and trust. In this paper, we analyze more than 33,000 AI-generated pull requests P...

GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attacks

Rule-based Intrusion Detection and Prevention Systems IDPS offer precise attack detection as well as mitigation, however their manually crafted, signature-driven rules limit adaptability to emerging and zero-day threats. Additionally, existing public datasets e.g., CICIDS2017, UNSW-NB15 focus on...

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent...

Kraken: Higher-Order EM Side-Channel Attacks on DNNs in near and Far Field

The multi-million dollar investment required for modern machine learning ML has made large ML models a prime target for theft. In response, the field of model stealing has emerged. Attacks based on physical side-channel information have shown that DNN model extraction is feasible, even on CUDA...

FROST: Fingerprinting Remotely Using OPFS-based SSD Timing

Prior work showed that variations in SSD access time can be used to leak information about user activity, e.g., the websites a user accesses, and for covert data transmission. To achieve this, SSD contention side channels require accurate high-resolution timing measurements of I/O operations, e.g...

YARA-X 1.17.0

YARA-X is a re-incarnation of YARA, a pattern matching tool designed with malware researchers in mind. This new incarnation intends to be faster, safer and more user-friendly than its predecessor. The ultimate goal of YARA-X is replacing YARA as the default pattern matching tool for malware...

SmartPoC: Generating Executable and Validated PoCs for Smart Contract Bug Reports

Smart contracts are prone to vulnerabilities and are analyzed by experts as well as automated systems, such as static analysis and AI-assisted solutions. However, audit artifacts are heterogeneous and often lack reproducible, executable PoC tests suitable for automated validation, leading to...

CLASP: Cost-Optimized LLM-Based Agentic System for Phishing Detection

Phishing websites remain a significant cybersecurity threat, necessitating accurate and cost-effective detection mechanisms. In this paper, we present CLASP, a novel system that effectively identifies phishing websites by leveraging multiple intelligent agents, built using large language models...

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents

Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers and advanced persistent threats achieve their objectives unnoticed; autonomous...

Description-Code Inconsistency in Real-World MCP Servers: Measurement, Detection, and Security Implications

The Model Context Protocol MCP has emerged as a critical standard empowering Large Language Models LLMs to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool...

API Security Based on Automatic OpenAPI Mapping

This paper presents Map Reduce Graph MRG, a novel unsupervised method for modeling and securing HTTP REST APIs. MRG learns API structure from real-world traffic without prior knowledge or labels, automatically generating OpenAPI-compliant documentation by reconstructing routes, methods, and...

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...

(A)ISpy: Parasitic Trojans for Machine Learning Infrastructure

Modern machine learning ML pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current practices audit data and model artifacts or rely on file integrity checks, the execution environment remains implicitly trusted. This blind spot enables acti...

A Longitudinal Study of Android Apps Signing Key Protection

Android app signing relies on developer-managed credentials, making secure key protection essential for the integrity of the software supply chain. A recent platform key leakage incident involving two major OEM manufacturers demonstrates that even robustly designed signing mechanisms can be...

FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction

Software vulnerabilities pose critical security threats, with nearly 50,000 CVEs reported in 2025. While Large Language Models LLMs show promise for automated vulnerability detection, three key challenges remain. First, LLM-generated vulnerability reports suffer from high false positive rates and...

Measuring and Evaluating the Performance of Generative AI Models for Scam Detection

Online scams continue to cause substantial financial and personal harm. As a result, detection systems based on Large Language Models LLMs have been integrated into security products ranging from email gateways and browser extensions to fraud-monitoring dashboards. As this adoption accelerates, a...

Deep Learning-Based Binary Analysis for Vulnerability Detection in X86-64 Machine Code

While much of the current research in deep learning-based vulnerability detection relies on disassembled binaries, this paper explores the feasibility of extracting features directly from raw x86-64 machine code. Although assembly language is more interpretable for humans, it requires more comple...

BrowseSafe: Understanding and Preventing Prompt Injection within AI Browser Agents

The integration of artificial intelligence AI agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web agents, yet the resulting impact within real-world environments...

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...

VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution

As software systems grow in complexity, security vulnerabilities have become increasingly prevalent, posing serious risks and economic costs. Although automated detection tools such as fuzzers have advanced considerably, effective resolution still often depends on human expertise. Existing...

PromoGuardian: Detecting Promotion Abuse Fraud with Multi-Relation Fused Graph Neural Networks

As e-commerce platforms develop, fraudulent activities are increasingly emerging, posing significant threats to the security and stability of these platforms. Promotion abuse is one of the fastest-growing types of fraud in recent years and is characterized by users exploiting promotional activiti...

SecureAgentBench: Benchmarking Secure Code Generation under Realistic Vulnerability Scenarios

Large language model LLM powered code agents are rapidly transforming software engineering by automating tasks such as testing, debugging, and repairing, yet the security risks of their generated code have become a critical concern. Existing benchmarks have offered valuable insights but remain...

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

The authors of this paper release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline trajectories across three frontier...

PromptLocate: Localizing Prompt Injection Attacks

Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected prompt, which consists of injected instructions and data. Localizing the injected prompt within contaminated data is...

CyberChainBench: Can AI Agents Secure Smart Contracts against Real-World On-Chain Vulnerabilities?

We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability detection, exploit generation, and patch synthesis. Built from 541 real-world exploit incidents from DeFiHackLabs spanning 9 EVM chains, the benchmark...

APT-Agent: Automated Penetration Testing Using Large Language Models

Penetration testing is essential to securing modern web infrastructures, yet traditional manual methods struggle to keep pace with their scale and complexity. Large Language Models LLMs offer new opportunities for automating these tasks, but existing approaches face two persistent challenges:...

CAVGAN: Unifying Jailbreak and Defense of LLMs Via Generative Adversarial Attacks on Their Internal Representations

Security alignment enables the Large Language Model LLM to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM jailbreak attacks and defenses. We analyze the security protection...

Breaking Isolation: A New Perspective on Hypervisor Exploitation Via Cross-Domain Attacks

Hypervisors are under threat by critical memory safety vulnerabilities, with pointer corruption being one of the most prevalent and severe forms. Existing exploitation frameworks depend on identifying highly-constrained structures in the host machine and accurately determining their runtime...