Towards Scalable and Cost-Efficient Vulnerability Detection: A Study on Automatic Query Generation

Static analysis remains a cornerstone of software security, yet the effectiveness of tools such as CodeQL is often limited by the substantial manual effort required to develop high-coverage query suites. While large language models LLMs have emerged as a potential solution for automated code...

No-Box Vulnerability Analysis: Description-Only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted, critical in situ systems, or commercially gated software. Therefore, we propose a new paradigm of no-box...

An Empirical Analysis of ReDoS Vulnerabilities and ReDoS Detection Tools

ReDoS vulnerabilities are a type of denial of service software weakness that occurs when a regex is used to validate user-supplied input. In some cases, the regex matching process can take exponential time, leading to a denial of service. In this study, we examine and compare the effectiveness of...

DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents

When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it...

PT-2026-102364

Name of the Vulnerable Software and Affected Versions PyJWT versions 2.13.0 through 2.13.x Description An issue exists in the HMACAlgorithm.prepare key function within jwt/algorithms.py where the raw-JWK detector fails to normalize Unicode byte-order marks BOM before JSON validation. When a publi...

CVE-2026-53637 Sylius: Cart FormComponent allows modification or deletion of an already-completed order

Sylius is an Open Source eCommerce Framework on Symfony. Versions 2.0.0 through 2.0.17, 2.1.0 through 2.1.14, and 2.2.0 through 2.2.5 contain an improper workflow enforcement vulnerability in the cart FormComponent. When an order is completed while its cart page remains open, the stale...

Aegis aegis-v0.14.1-alpha

AEGIS is a desktop app for monitoring local AI agents and reviewing their files and selected actions. Inspect processes, sensitive-file observations, TCP endpoints and attribution evidence in Observatory. Monitoring requires no agent plugin; policy-controlled execution and MCP action tools requir...

SkillSpector v2.11.1

SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. In the 31,132-skill analyzed...

CVE-2025-14208

creationtimestamp| type| source ---|---|--- 2026-09-08 10:00:03+00:00| seen| The Shadowserver honeypot/common-vulnerabilities - 2026-09-07 2026-09-08 11:00:34+00:00| exploited| https://vulnerability.circl.lu/known-exploited-vulnerabilities-catalog/12253a70-6b5a-44ad-b30d-9849e4011cb8 2026-09-09...

Watcher v3.5.3

AI-Powered Automated Cybersecurity Threat Detection Platform Watcher is a Django & React JS platform designed to discover and monitor emerging cybersecurity threats with AI-powered threat intelligence analysis. It can be deployed on webservers or quickly run via Docker. Watcher Capabilities Watch...

LLMSec-AV: A Vulnerability Taxonomy and LLM-Driven Software Weakness Discovery Framework for Autonomous Vehicles

Automated vehicles rely on millions of lines of safety-critical software, yet general-purpose analyzers do not understand which code can affect vehicle motion. This study asks whether large language models LLMs with explicit automated-vehicle AV security knowledge improve weakness detection beyon...

HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving

We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for intelligence. Existing defenses embed traps inside...

Navigating the Latent Manifold: Proactive Concept Drift Adaptation for Resilient NIDS

Network intrusion detection systems NIDS are critical for cybersecurity, safeguarding services and data from potential attacks. However, existing AI-based NIDS often assume static data distributions and fail to handle concept drift, leading to degraded performance and increased false positives in...

Windows Malware Detector As a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness

Industrial Windows malware detectors are commonly described as Compound AI Systems composed of multiple heterogeneous components, including rule-based mechanisms as well as machine-learning-based static and dynamic analyses. However, due to industrial secrecy and limited public disclosure, the...

yj_nearbyglasses v1.0.10

yjnearbyglasses attempting to detect smart glasses nearby and warn you. ⚠ WARNING! ⚠ nearby-glasses-alert.pages.dev is NOT RELATED TO MY PROJECT. Many apps in Play Store and App Store look or are even called very similar to Nearby Glasses. They seem to hijack the name and try to make a quick prof...

ultralytics v8.4.142

中文 | 한국어 | 日本語 | Русский | Deutsch | Français | Español | Português | Türkçe | Tiếng Việt | العربية Ultralytics creates cutting-edge, state-of-the-art SOTA YOLO models built on years of foundational research in computer vision and AI. Constan...

Flintlock

Flintlock Hardware-assisted memory sandboxing for high-freq...

LLM-Based Penetration Testing in the Presence of Honeypots

Large language model LLM agents are increasingly employed for offensive cybersecurity tasks such as automated vulnerability discovery, reconnaissance, and penetration testing. This new capability also threatens one of the defender's most valuable tools: deception. Traditional honeypots rely on...

Frequency-Domain Mixing Data Augmentation for Malicious Traffic Detection

The strong dynamics of network traffic often force malicious traffic detection models to handle out-of-distribution data. Typically, deep learning-based malicious traffic detection models require a large amount of high-quality training data. However, owing to challenges such as high labeling...

Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection

Anomaly-based intrusion detection systems in industrial control systems ICS and operational technology OT environments are increasingly required to meet formal resilience criteria: absorbed adversarial disturbances, graceful degradation under sustained attack, and certified system-level guarantee...