GNUnet P2P Framework 0.26.2

GNUnet is a peer-to-peer framework with focus on providing security. All peer-to-peer messages in the network are confidential and authenticated. The framework provides a transport abstraction layer and can currently encapsulate the network traffic in UDP IPv4 and IPv6, TCP IPv4 and IPv6, HTTP, o...

AI Agents May Always Fall for Prompt Injections

Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm data-instruction separation both fails to detect attacks that operate through contextual manipulation and degrades contextually appropriate behavior. We...

IServ Schoolserver User Enumeration

IServ Schoolserver suffers from a user enumeration vulnerability. The vendor does not feel this is an issue...

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that spans websites and sessions. While existing security research on memory assumes attackers can directly...

CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-To-End Cybersecurity Capabilities

AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. However, existing cybersecurity evaluations of AI systems are limited in scale or scope, and fail to capture the end-to-end lifecycle of real-world...

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...

PBFuzz: Agentic Directed Fuzzing for PoV Generation

Proof-of-Vulnerability PoV input generation is a critical task in software security and supports downstream applications such as path generation and validation. Generating a PoV input requires solving two sets of constraints: 1 reachability constraints for reaching vulnerable code locations, and ...

Everything You Wanted to Know about LLM-Based Vulnerability Detection but Were Afraid to Ask

Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a critical question remains: Are LLMs truly effective at detecting real-world vulnerabilities? Current evaluations, which...

ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

Large language models LLMs are increasingly being deployed as software engineering agents that autonomously contribute to repositories. A major benefit these agents present is their ability to find and patch security vulnerabilities in the codebases they oversee. To estimate the capability of...

PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities

Software vulnerabilities are increasing at an alarming rate. However, manual patching is both time-consuming and resource-intensive, while existing automated vulnerability repair AVR techniques remain limited in effectiveness. Recent advances in large language models LLMs have opened a new paradi...

AgentSentinel: an End-To-End and Real-Time Security Defense Framework for Computer-Use Agents

Large Language Models LLMs have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature of LLM outputs, they may issue unintended tool commands or...

Automating Function-Level TARA for Automotive Full-Lifecycle Security

As modern vehicles evolve into intelligent and connected systems, their growing complexity introduces significant cybersecurity risks. Threat Analysis and Risk Assessment TARA has therefore become essential for managing these risks under mandatory regulations. However, existing TARA automation...

VulnGym: Evaluating Vulnerability Management Strategies against Advanced Persistent Threats

Enterprise networks are continuously targeted by Advanced Persistent Threats APTs, attack campaigns exploiting software vulnerabilities to compromise critical assets over time. As disclosed vulnerabilities grow, resource-constrained organizations must prioritize which ones to patch. Existing...

A Framework for Formalizing LLM Agent Security

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However,...

Virtual Camera Detection: Catching Video Injection Attacks in Remote Biometric Systems

Face anti-spoofing FAS is a vital component of remote biometric authentication systems based on facial recognition, increasingly used across web-based applications. Among emerging threats, video injection attacks -- facilitated by technologies such as deepfakes and virtual camera software -- pose...

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents

Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as exploitation success. That single binary outcome collapses the hard...

A Comprehensive Study on the Impact of Vulnerable Dependencies on Open-Source Software

Open-source libraries are widely used by software developers to speed up the development of products, however, they can introduce security vulnerabilities, leading to incidents like Log4Shell. With the expanding usage of open-source libraries, it becomes even more imperative to comprehend and...

QLCoder: A Query Synthesizer for Static Analysis of Security Vulnerabilities

Static analysis tools provide a powerful means to detect security vulnerabilities by specifying queries that encode vulnerable code patterns. However, writing such queries is challenging and requires diverse expertise in security and program analysis. To address this challenge, we present QLCoder...

deepSURF: Detecting Memory Safety Vulnerabilities in Rust through Fuzzing LLM-Augmented Harnesses

Although Rust ensures memory safety by default, it also permits the use of unsafe code, which can introduce memory safety vulnerabilities if misused. Unfortunately, existing tools for detecting memory bugs in Rust typically exhibit limited detection capabilities, inadequately handle Rust-specific...

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...

Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection for Repository-Scale Codebases

Memory safety vulnerabilities remain a significant threat even for projects with extensive fuzzing and manual auditing. Recent results suggest that large language models hold great promise for detecting such vulnerabilities, but they are unreliable, at risk of hallucination, and challenging to...

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifiers cannot adapt to these evolving attacks, while adaptive memory-based guardrails tend to over-refuse benign queries that resemble stored attacks...

Automatically Attacking Software Reverse Engineering AI Agents

Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models LLM, agentic systems enabled with tools, such as...

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...

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation

Retrieval-Augmented Generation RAG has proven effective in mitigating hallucinations in large language models by incorporating external knowledge during inference. However, this integration introduces new security vulnerabilities, particularly to poisoning attacks. Although prior work has explore...

A Hard-Label Black-Box Evasion Attack against ML-Based Malicious Traffic Detection Systems

Machine Learning ML-based malicious traffic detection is a promising security paradigm. It outperforms rule-based traditional detection by identifying various advanced attacks. However, the robustness of these ML models is largely unexplored, thereby allowing attackers to craft adversarial traffi...

Broken Object Level Authorization in the Wild: An Empirical Taxonomy from 100+ Bug Bounty Disclosures

Broken Object Level Authorization BOLA is consistently ranked the most critical API security vulnerability, yet the existing literature remains almost entirely conceptual. This paper presents one of the first large-scale empirical analyses of BOLA in publicly disclosed bug bounty reports. We...

Under the Hood of SKILL.Md: Semantic Supply-Chain Attacks on AI Agent Skill Registry

Autonomous AI agents increasingly extend their capabilities through Agent Skills: modular filesystem packages whose SKILL.md files describe when and how agents should use them. While this design enables scalable, on-demand capability expansion, it also introduces a semantic supply-chain risk in...

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...

LLM Agent Safety, Multi-Turn Red-Teaming, Jailbreak Benchmarks, Adversarial Robustness, Safety-Critical Systems

Large language model LLM agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as...

From Frontier to Shadow AI: A Simmering Threat to Assurance and Security in Critical Infrastructure

Frontier AI systems, including large language models and emerging agentic AI tools, offer significant operational benefits but present unique challenges to critical infrastructure CI environments due to their non-deterministic and emergent properties. While formal adoption is inherently cautious...

From Transactions to Exploits: Automated PoC Synthesis for Real-World DeFi Attacks

Blockchain systems are increasingly targeted by on-chain attacks that exploit contract vulnerabilities to extract value rapidly and stealthily, making systematic analysis and reproduction highly challenging. In practice, reproducing such attacks requires manually crafting proofs-of-concept PoCs, ...

CUSTOS: Toward Forensic-Ready Zero Trust at the Capture-Containment Boundary

Zero Trust ZT replaces implicit trust with continuous verification, but mutual TLS, ephemeral workloads, identity-centric control, and automated remediation reduce payload visibility, weaken IP-based attribution, and shrink the window for acquiring volatile evidence. We propose CUSTOS, a...

WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents

WebMCP is a newly emerging protocol that enables websites to expose tools directly to AI agents, bypassing traditional user interfaces and introducing new security risks. The dynamic exposure of agent-accessible tools in WebMCP expands the attack surface of web sessions, especially when third-par...

WordPress TI WooCommerce Wishlist 2.9.2 Arbitrary File Upload

WordPress TI WooCommerce Wishlist plugin versions 2.9.2 and below suffer from an arbitrary file upload vulnerability...

SkillGuard: A Permission Framework for Agent Skills

Agent skills extend LLM agents with reusable instructions, scripts, tool bindings, and contextual dependencies. However, current skill ecosystems largely rely on trust-based loading and static inspection, leaving a gap between what a skill can inject into an agent's context and what it can cause...

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...

CTFusion: A CTF-Based Benchmark for LLM Agent Evaluation

Recent advances in Large Language Models LLMs have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag CTF benchmarks. However, current CTF benchmarks reuse existing...

TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition

In this paper, the researchers show that the security guarantees of modern TEE offerings by Intel and AMD can be broken cheaply and easily, by building a memory interposition device that allows attackers to physically inspect all memory traffic inside a DDR5 server...

CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection

Detecting source code vulnerabilities is increasingly difficult as modern security flaws are rooted in complex causal dependencies between execution flows, control conditions, and program states. Despite recent advances in Large Language Models LLMs and multi-agent frameworks, existing approaches...

ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense

LLM-driven automated penetration testing agents are typically evaluated against static targets that neither detect nor respond to attacks, so their behavior under intelligent defense remains untested. The causal consistency of multi-step attack chains likewise hinges on unstable LLM reasoning, an...

Adversarial-Resilient RF Fingerprinting: A CNN-GAN Framework for Rogue Transmitter Detection

Radio Frequency Fingerprinting RFF has evolved as an effective solution for authenticating devices by leveraging the unique imperfections in hardware components involved in the signal generation process. In this work, we propose a Convolutional Neural Network CNN based framework for detecting rog...

Apple Security Advisory 03-31-2025-7

Apple Security Advisory 03-31-2025-7 - macOS Sequoia 15.4 addresses buffer overflow, bypass, code execution, format string, heap corruption, integer overflow, out of bounds read, out of bounds write, spoofing, and use-after-free vulnerabilities...

SEC-Bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

Large language models LLMs now support automated software security tasks, including vulnerability discovery and proof-of-concept PoC generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios because they rely on fuzzing harnesses, target-specific...

From Storage to Steering: Memory Control Flow Attacks on LLM Agents

Modern agentic systems allow Large Language Model LLM agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and execution. Existing security analyses often treat these control flows as ephemeral, one-off sessions, overlooking the persisten...

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...

Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection

Fairness is a core element in the trustworthy deployment of deepfake detection models, especially in the field of digital identity security. Biases in detection models toward different demographic groups, such as gender and race, may lead to systemic misjudgments, exacerbating the digital divide...

Exploiting LLM Agent Supply Chains Via Payload-Less Skills

Autonomous agents powered by Large Language Models LLMs acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for systematic security evaluation. Current auditing mechanisms a...

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...

GraphQLer: Enhancing GraphQL Security with Context-Aware API Testing

GraphQL is an open-source data query and manipulation language for web applications, offering a flexible alternative to RESTful APIs. However, its dynamic execution model and lack of built-in security mechanisms expose it to vulnerabilities such as unauthorized data access, denial-of-service DoS...