
PurpleLlama
Set of tools to assess and improve LLM security.

Set of tools to assess and improve LLM security.

Obfuscates JavaScript and Node.js code with variable renaming, string encryption, control flow flattening, and anti-debugging to protect source code…

Simple Anti-cheat library for applications that use C++ on windows. #PastedProtection

An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.

The Security Toolkit for LLM Interactions

NOVA - Claude Code Protection System against prompt injection attacks

[NeurIPS '25] Code for Paper "IF-Guide: Influence Function-Guided Suppression of Harmful Training Data for Reducing LLM Toxicity"

🐍 🔍 GuardDog is a CLI tool to Identify malicious PyPI and npm packages

Spartacus DLL/COM Hijacking Toolkit

a guard that blocks catastrophic agent actions

Pre-execution intent verification for AI agents. Audits what your AI is about to do, not what it says. Zero dependencies, deterministic, hash-sealed.

DOMPurify - a DOM-only, super-fast, uber-tolerant XSS sanitizer for HTML, MathML and SVG. DOMPurify works with a secure default, but offers a lot of…

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

A Solution For Cross-Platform Obfuscated Commands Detection presented on CIS2019 China. 动静态Bash/CMD/PowerShell命令混淆检测框架 - CIS 2019大会

Real-time npm/PyPI supply-chain threat detection. Behavioral chain analysis, AST scanning, IOC feeds, and compound scoring engine.

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

Security module for php7 and php8 - Killing bugclasses and virtual-patching the rest!

Anticipator is an open-source threat detection platform for multi-agent AI systems.