frida-c2-mcp

FridaC2MCP An MCP server with streamable HTTP transport that runs Frida's dynamic instrumentation entirely on-device — no client-side tooling required. This project runs directly on rooted Android and jailbroken iOS devices , exposing Frida as a set of tools callable over HTTP. Any MCP-compatible...

on-device-browser-agent

Local Browser - Automatización Web con IA en Dispositivo Pronto lanzaremos soporte para runanywhere-web-sdk en nuestro repositorio principal: échale un vistazo: https://github.com/RunanywhereAI/runanywhere-sdks Una extensión de Chrome que utiliza WebLLM para ejecutar automatización web con IA...

Project-Pwnag0dchi

Proyecto Pwnag0dchi Creé esto porque mucha gente preguntaba sobre los plugins personalizados y configuraciones que uso. Siguiendo esta guía, tu Pwnagotchi se verá exactamente como se ve en mis redes sociales y videos de YouTube en 5 minutos como máximo. También encontrarás una guía completa de...

androidReverse

Android Reverse Un conjunto de herramientas de ingeniería inversa que se ejecuta completamente en Android. Sin PC, sin ADB, sin herramientas de escritorio: todo, desde la extracción de APK hasta el análisis, edición y reconstrucción de binarios nativos, se realiza en el propio dispositivo. Servid...

Awesome-MoAI-Security

Awesome Mobile On-Device AI Security Seguridad de IA en Dispositivos Móviles SoK: Landscape de Ataques y Defensas de los Sistemas de IA en Dispositivos Móviles Los sistemas de IA en dispositivos móviles ejecutan modelos de IA localmente a través de frameworks de ML como LiteRT/TFLite , Core ML ,...

nfcgate

NFCGate ⚠️NFCGate is currently being falsely detected as "NGate" malware. Please seethis issue for up-to-date information.⚠️ NFCGate is an Android application meant to capture, analyze, or modify NFC traffic. It can be used as a researching tool to reverse engineer protocols or assess the security...

HydraDragonAV-Mobile

🐉 HydraDragonAV Mobile Advanced Android Antivirus With Threat Protection ⚠️ Project on hold. This project did not get enough interest, so I have paused it for a while. Development has moved to HydraDragonAntivirus. Discord Community Server: https://discord.gg/7XMCuj5mbP Logo made by discord user...

abdal-lockbox

🔐 Abdal LockBox 🌐 Read in your language: 🇬🇧 English | 🇨🇳 中文 | 🇷🇺 Русский | 🇪🇸 Español | 🇯🇵 日本語 | 🇮🇷 فارسی | 🇸🇦 العربية | 🇹🇷 Türkçe | 🇩🇪 Deutsch | 🇮🇳 हिन्दी Secure. Store. Autofill. — A privacy-first Android password manager by Abdal Security Group. Abdal LockBox keeps your credentials encrypted on...

Stego-Lab

Stego-Lab Steganography. EXIF. Watermarks. Decode. Batch. Professional image privacy workflows for iPhone, iPad, and macOS. Website · GitLab · Project Page · Privacy Policy · Press Kit · Support · License Why Stego-Lab Stego-Lab brings together workflows that are usually scattered across multiple...

Exploit for Heap-based Buffer Overflow in Libarchive

CVE-2025-5915 — libarchive RAR v4 heap over-read with on-devi...

PT-2026-64895

A lack of authentication in the mobile app APK v5.5.0 for Ghost Robotics' Vision 60 robot allows an unauthenticated attacker connected to the device's internal Wi-Fi network to gain unrestricted access to the web administration interface and the HTTP API. Due to the lack of authorization...

CVE-2026-65058 Trezor Safe improper security check in on-device display

Trezor Safe 3, Safe 5, and Safe 7 firmware contains a confirmation-binding flaw in the Ethereum signtx / signtxeip1559 flow. For contract interactions, the device confirms only the initial calldata chunk while the signature commits to the full streamed calldata. An attacker could present calldata...

CVE-2026-65058

The CVE-2026-65058 affects Trezor Safe firmware 3, 5, and 7, where a confirmation-binding flaw in the Ethereum sign_tx / sign_tx_eip1559 flow allows an attacker to present calldata and later supply a different tail, changing the signed transaction while only the initial calldata chunk is confirme...

CVE-2026-65058 Trezor Safe improper security check in on-device display

Trezor Safe 3, Safe 5, and Safe 7 firmware contains a confirmation-binding flaw in the Ethereum signtx / signtxeip1559 flow. For contract interactions, the device confirms only the initial calldata chunk while the signature commits to the full streamed calldata. An attacker could present calldata...

Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms

The need for secure and private Artificial Intelligence AI and Machine Learning ML on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an ever-increasing number of pre-trained AI models being used o...

CVE-2026-46061

In the Linux kernel, the following vulnerability has been resolved: jbd2: fix deadlock in jbd2journalcancelrevoke Commit f76d4c28a46a "fs/jbd2: use sleeping version of findgetblock" changed jbd2journalcancelrevoke to use findgetblocknonatomic which holds the folio lock instead of iprivatelock. Th...

Speed Kills: Exploring Confused Deputy Attacks through Edge AI Accelerators

AI Accelerator AIA are specialized hardware e.g., Tensor Processing Unit TPU, that enable optimal and efficient execution of AI applications and on-device inference. The growing demand for AI applications has led to the widespread adoption of AIAs on Edge or embedded devices on Edge or embedded...

Google Chrome’s silent 4GB AI download problem [updated]

Google Chrome has been quietly downloading a 4GB AI model onto users' devices without asking first. Security researcher Alexander Hanff, aka ThatPrivacyGuy, reports that Chrome has been silently installing Gemini Nano, Google's on-device AI model, as a file called weights.bin stored in the...

WOOTdroid: Whole-System Online On-Device Tracing for Android

System auditing on Android faces two problems. First, existing syscall tracers lose events under load, silently overwriting entries faster than a user space reader can drain them. Second, security-relevant application behavior is mediated through Binder, Android's kernel IPC mechanism, and is...

Agentic Knowledge Distillation: Autonomous Training of Small Language Models for SMS Threat Detection

SMS-based phishing smishing attacks have surged, yet training effective on-device detectors requires labelled threat data that quickly becomes outdated. To deal with this issue, we present Agentic Knowledge Distillation, which consists of a powerful LLM acts as an autonomous teacher that fine-tun...