ai-llm-red-team-handbook

AI / LLM Red Team Field Manual & Consultant's Handbook A comprehensive operational toolkit for conducting AI/LLM red team assessments on Large Language Models, AI agents, RAG pipelines, and AI-enabled applications. This repository provides both tactical field guidance and strategic consulting...

Awesome-MoAI-Security

Awesome Mobile On-Device AI Security SoK: Attack and Defense Landscape of Mobile On-device AI Systems Mobile on-device AI systems execute AI models locally through ML frameworks such as LiteRT/TFLite , Core ML , ExecuTorch , ONNX , and hardware-backed accelerators. This repo tracks the security...

wolfCOSE

wolfCOSE wolfCOSE is a lightweight and fast C library implementing core CBOR and COSE standards, backed by wolfSSL for cryptography. Supported Standards & RFCs Core Specifications: RFC 8949 - Concise Binary Object Representation CBOR RFC 9052 - CBOR Object Signing and Encryption COSE RFC 9053 -...

vex8s

Vex8s this logo is not AI generated Vex8s generates VEX documents by correlating container vulnerabilities with Kubernetes settings to determine which CVEs are actually exploitable in your cluster. Please note, this is an experimental project. Things might change quickly. How It Works The project...

SecML

SecML: A library for Secure and Explainable Machine Learning SecML is an open-source Python library for the security evaluation of Machine Learning ML algorithms. It comes with a set of powerful features: Wide range of supported ML algorithms. All supervised learning algorithms supported by...

frostbyte

FrostByte Progolue: In the past few days I've been experimenting with the AppDomain manager injection technique had a decent success with it in my previous Red Team engagements against certain EDRs. Although, this is really good for initial access vector, I wanted to release a POC which will help...

CVE-2025-10951

CVE-2025-10951 - checkmlloggertraversal.py Proof-of-existence checker for CVE-2025-10951 / GHSA-8x9j-2p8r-7xc6 — an unauthenticated path traversal in geyang/ml-logger ≤ 0.10.36, affecting the loghandler / streamhandler functions in mllogger/server.py. For use only against systems you are authoriz...

vger

V'ger V'ger is an interactive command-line application for post-exploitation of authenticated Jupyter instances with a focus on AI/ML security operations. User Stories As a Red Teamer , you've found Jupyter credentials, but don't know what you can do with them. V'ger is organized in a format that...

Damn-Vulnerable-ML-Model

This repository does not have a README...

Final-project-SQL-injection-pipeline

SQL Injection Detection — Hybrid ML Pipelines Source code for the MSc dissertation: Enhancing Web Application Firewall with Machine Learning for SQL Injection Detection | ---|--- Author| Lilliane Linnet Musoke Institution| University of Reading, Department of Computer Science Programme| MSc Data...

ai-exploits

AI Exploits The AI world has a security problem and it's not just in the inputs given to LLMs such as ChatGPT. Based on research done by Protect AI and independent security experts on the Huntr Bug Bounty Platform, there are far more impactful and practical attacks against the tools, libraries an...

Aliens_eye

ALIENS EYE AI-OSINT Username Scanner Advanced AI-Powered Social Media Username Finder Scan 840+ platforms with ML-blended detection 🐧 New from the author: lxask lxask is a Linux command assistant that runs entirely on your own machine: describe what you want in plain English and it suggests the...

PIIHunter

AI PII Scanner An internal security tool for discovering Personally Identifiable Information PII in PostgreSQL databases and Jira projects Overview The AI PII Scanner is a comprehensive, security-focused tool designed for Application Security and Privacy teams to discover and catalog PII. It...

purple-team-exercise-framework

Purple Team Exercise Framework PTEF The Purple Team Exercise Framework PTEF is the industry standard methodology for designing and executing collaborative security exercises that bring together Cyber Threat Intelligence CTI, Red Teams, and Blue Teams. Purple Team Exercises are an efficient method...

gha-lab-40e23db109

Automated research artifact — not the upstream project. This repository is a disposable lab built by an automated harness for a master's thesis at Université Laval on reproducing published GitHub Actions workflow vulnerabilities. It is a verbatim snapshot of gradio-app/gradio at commit...

fickling

Fickling Fickling is a decompiler, static analyzer, and bytecode rewriter for Python pickle object serializations. You can use fickling to detect, analyze, reverse engineer, or even create malicious pickle or pickle-based files, including PyTorch files. Fickling can be used both as a python libra...

GuardModel

GuardModel Block malicious AI models in your pipeline with one line of YAML. GuardModel is a GitHub Action that automatically scans ML model files for malicious code, vulnerabilities, and security risks in CI/CD pipelines. It blocks dangerous models before they reach production by detecting pickl...

H2O ImportFiles - Local File Inclusion

An attacker is able to read any file on the server hosting the H2O dashboard without any authentication. id: CVE-2023-6038 info: name: H2O ImportFiles - Local File Inclusion author: danmcinerney,byt3bl33d3r severity: high description: | An attacker is able to read any file on the server hosting t...

ejbca-pqc-lab

EJBCA Pure PQC Lab — ML-DSA-65 Two-Tier PKI Hierarchy A hands-on implementation of NIST FIPS 204 ML-DSA in a two-tier PKI hierarchy using EJBCA Community Edition. 📖 Full walkthrough: Building a Post-Quantum PKI: How I Signed a Root CA and Sub CA Using ML-DSA on EJBCA What This Lab Builds A comple...

mlkem-native

mlkem-native mlkem-native is a secure, fast, and portable C90^C90 implementation of ML-KEM^FIPS203. It is a fork of the ML-KEM reference implementation^REF. All C code in mlkem/src/ and mlkem/src/fips202/, except for the backends for platforms other than AArch64 and x8664 and the debug code, is...