#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
hannahbellesheart/blackbox.ai.security.analysisSecurity analysis tool identifying risks in Blackbox.ai extensions, including credential harvesting, unpatched CVEs, and privacy threats from hidden…
sydsec1/sydAir-gapped cybersecurity assistant for security professionals. 100% offline AI-powered analysis tool for Nmap, Volatility, BloodHound, Metasploit,…
sydsec/sydOffline AI Security Assistant for Air-Gapped Pentesting
rulebricks/claude-code-guardrailsReal-time guardrails for Claude Code tool calls.
leviticus-triage/cerebro-red-v2CEREBRO-RED v2: Advanced LLM Red Team Research Platform with PAIR Algorithm and LLM-as-a-Judge Evaluation
seanheelan/anamnesis-releaseEvaluation framework for studying LLM agents that automatically generate working exploits from vulnerability reports, bypassing modern security…
runanywhereai/on-device-browser-agentOn-device AI browser automation using WebLLM. No cloud, no API keys, fully private.
borenstein/yolo-cageAI coding agents that can't exfiltrate secrets or merge their own PRs.
preludeorg/cua-kitTools for attacking Computer Use Agents
thebabush/llvm-jutsuAnti-LLM obfuscation via finger counting
aloshdenny/reverse-synthid-textreverse engineering SynthID for text
secml/secmlA Python library for Secure and Explainable Machine Learning Documentation available @ https://secml.gitlab.io Follow us on Twitter @…
owasp/www-project-top-10-for-large-language-model-applicationsOWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)
lcbower33/stegoscanAutomated steganography detection tool that scans websites, web servers, and local directories using AI-driven object/text recognition and deep file…
lglznl/klaiosKLAIOS is a hybrid security environment that merges Kali Linux’s offensive toolkit with hardened, VPN-bunker-style isolation—enhanced by modern AI…
matank001/moxyMoxy is an open-source DAST tool designed for modern web application security testing. It provides an easy-to-use interface with agentic capabilities…
trailofbits/anamorpherimage scaling attacks for multi-modal prompt injection
nova-hunting/nova-tracerNOVA - Claude Code Protection System against prompt injection attacks
