
skill-scanner
Security Scanner for Agent Skills

Security Scanner for Agent Skills

Static analysis of malicious Python code

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

ML-based detection of Zombie ZIP archive header evasion attacks (CVE-2026-0866)

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

This Repository is created after my own research into malicious browser extensions, by brining the work of many others and news articles into one…

Memory-free continual learning framework for malware classification using mode connectivity-based interpolation. Supports class-incremental and…

takes shellcode bad-bytes and banishes them, returning cleaned shellcode with preserved functionalities

image scaling attacks for multi-modal prompt injection

Graph-based threat detection system using inexact graph vector matching to compare threat graphs with CTI-derived attack query graphs for automated…

Proof-of-concept exploit for CVE-2025-32434, a pickle deserialization vulnerability in PyTorch's weights_only mode, demonstrating malicious tar file…

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.


Re-play Security Events

A machine learning tool that ranks strings based on their relevance for malware analysis.

CERTITUDE - A python package to classify URLs as malicious or benign

SAFE embeddings to match functions in yara

DGA Domain Detection using Bigram Frequency Analysis