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

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

A security scanner for your LLM agentic workflows

An advanced in-memory evasion technique fluctuating shellcode's memory protection between RW/NoAccess & RX and then encrypting/decrypting its contents

Anti-LLM obfuscation via finger counting

The Security Toolkit for LLM Interactions

Source code about machine learning and security.

A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

Kali365 - EvilTokens Replica

Hardware Breakpoint (DR0-DR7) based patch-less user-mode hooking & telemetry instrumentation engine (AMSI, WLDP & ETW PoC).

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

Self-Defeating Audits: reproducible lab showing a low-privilege PostgreSQL role reversibly blinding a trigger-based auditor + poisoning attribution…

Demonstrates how a malicious Python package executes arbitrary commands during pip install via setup.py, highlighting PyPI supply chain and…

CVE-2026-20685 - Draft or TODO

Self-referenced local contrast for knowledge-poison detection in retrieval-augmented generation