agentic-ioc-scanner

agentic-ioc-scanner IOC scanner for agentic AI coding tools — detects Mini Shai-Hulud, Gemini CLI RCE, Cursor CVE-2026-26268, and DPRK PromptMink. A detection kit for compromise of agentic AI coding assistants Claude Code, Gemini CLI, Cursor and the dependencies they pull into your repos. Eleven...

sentinel-mcp

SentinelMCP — AI-Powered Cyber Defense System Google Cloud Hackathon submission — Autonomous threat detection and remediation orchestrated by Google Cloud Agent Builder Vertex AI Agent , powered by Gemini 2.0 Flash, Model Context Protocol MCP, and Dynatrace observability. The Problem Security tea...

statecraftcyber

Statecraft Cyber Intelligence Threat intelligence platform in Portuguese built from scratch as a personal Blue Team project. It aggregates data from global open sources and transforms it into technical briefings, classified news, enriched CVEs, and structured IOCs — all in PT-BR, continuously...

CVE-2026-2472-Vertex-AI-SDK-Google-Cloud

Unauthenticated Stored Cross-Site Scripting XSS in genai/evalsvisualization.py of Google Cloud Vertex AI SDK google-cloud-aiplatform versions from 1.98.0 up to but not including 1.131.0 - github.com/googleapis/python-aiplatform Author: Joshua Provoste N-day Researcher & Dev Credits: Din Asotić...

ai-code-review

🔍 codereview AI-powered code review in your terminal. One command. Instant feedback. Catches security vulnerabilities, bugs, and bad patterns before they hit production. Install · Quick Start · Usage · Providers · Contributing What It Does codereview sends your code to an LLM and returns a...

litellm-command-injection-security-assessment

CVE-2026-42271 - Inyección de Comandos MCP en LiteLLM AI Gateway que lleva a RCE Informe de Ciberseguridad al Estilo Consultor Informe profesional de evaluación de vulnerabilidades para el riesgo de inyección de comandos en LiteLLM, que incluye resumen ejecutivo, impacto técnico, remediación y...

Arisu

Arisu — Sistema automatizado de minería de claves de IA Arisu es una herramienta que escanea automáticamente repositorios de código públicos GitHub, GitLab, Gitee, Docker Hub, PyPI, npm, etc. y fragmentos de código Gist, Issues, CommonCrawl, extrae claves API de servicios de IA DeepSeek, OpenAI,...

aisecplus-week01-servicenow-ai-security-incident

AISec Plus Week01 - Mapa de la Amenaza Investigación de Incidentes de Seguridad en IA: Vulnerabilidad del Virtual Agent de ServiceNow CVE-2025-12420 ¿Qué Ocurrió? Se descubrió una vulnerabilidad crítica en la plataforma de IA de ServiceNow que permitía a un atacante no autenticado hacerse pasar p...

CVE-2026-39107

CVE-2026-39107: Cross-Site Scripting XSS en Kimi AI v1.0 Descripción Existe una vulnerabilidad de Cross-Site Scripting XSS en la función 'Preview' de la interfaz web de Kimi AI v1.0. La aplicación no sanea ni codifica adecuadamente las cargas útiles HTML/JavaScript generadas por el modelo de IA...

SecFlow

SecFlow Fully Automated Multi-Vector Threat Analysis Pipeline Drop in any file, URL, IP, domain, or image. SecFlow routes it through specialized analyzers, reasons about findings with AI, and produces a professional security report with YARA rules, SIGMA rules, and exportable PDF — automatically...

Securekit

Securekit Securekit protects what your models execute—across any AI system. Securekit is a protocol-agnostic security kernel for AI tool execution. It sits between any LLM or agent system and the tools they use, enforcing zero-trust execution, sandbox isolation, and policy-driven control. It is...

miasma-toolkit

Miasma / Shai-Hulud toolkit Incident analysis + detection/remediation tooling for the Miasma worm a Mini Shai-Hulud variant that injects auto-run payloads into AI-agent / IDE configs and npm/GitHub repos. ⚠️ Disclaimer — no warranty. This is a community defensive toolkit provided "as is" , without...

Mage AI - Insecure Default Authentication Setup

A vulnerability was found in Mage AI 0.9.75. It has been classified as problematic. This affects an unknown part. The manipulation leads to insecure default initialization of resource. It is possible to initiate the attack remotely. The complexity of an attack is rather high. The exploitability i...

Jordy Meow AI Engine - Unrestricted File Upload

Unrestricted Upload of File with Dangerous Type vulnerability in Jordy Meow AI Engine- ChatGPT Chatbot.This issue affects AI Engine- ChatGPT Chatbot- from n/a through 1.9.98. id: CVE-2023-51409 info: name: Jordy Meow AI Engine - Unrestricted File Upload author: pussycat0x severity: critical...

WordPress AI Engine Plugin - Token Exposure

Unauthenticated sensitive information exposure in AI Engine WordPress plugin = 3.1.3 exposes bearer tokens via REST API endpoints when No-Auth URL is enabled. id: CVE-2025-11749 info: name: WordPress AI Engine Plugin - Token Exposure author: 4m3rr0r severity: critical description: | Unauthenticat...

Kubio AI Page Builder <= 2.5.1 - Local File Inclusion

The Kubio AI Page Builder plugin for WordPress is vulnerable to Local File Inclusion in all versions up to, and including, 2.5.1 via thekubiohybridthemeloadtemplate function. This makes it possible for unauthenticated attackers to include and execute arbitrary files on the server, allowing the...

RvbbitSafe

RvbbitSafe: The Hacker's Nightmare – A Six-Fortress Anti-Ransomware Architecture for Windows 🛡️ Overview RvbbitSafe is a research prototype demonstrating a paradigm shift in ransomware defense. It's an active, multi-layered fortress that combines hardware virtualization, AI-driven deception,...

Mahoraga-Webapp-Defender

Mahoraga Webapp Defender AI-powered reactive webapp defense system designed to withstand AI-powered hacks in real-time. Table of Contents Mahoraga Webapp Defender Table of Contents Introduction Target Website Mahoraga Defender Architecture Dual Environments Agent Pipeline How to Start Getting rea...

CVE-2026-54519

CVE-2026-54519 ai-agent-automation missing ownership checks in memory APIs allowed cross-user memory read and deletion. Primary advisory: GHSA-qv97-83w4-ff86 Researcher credit: @chaitanyagarware At a Glance Field| Value ---|--- CVE| CVE-2026-54519 GHSA| GHSA-qv97-83w4-ff86 Project|...

TarantuBench

TarantuBench v1 A benchmark for evaluating AI agents on web security challenges, generated by the TarantuLabs engine. What is this? TarantuBench is a collection of 100 vulnerable web applications, each containing a hidden flag TARANTU.... An agent's job is to find and extract the flag by...