#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)

A collection of real-world threat model examples across various technologies, providing practical insights into identifying and mitigating security…

I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in…

Anti-LLM obfuscation via finger counting

LLM agent solving traces, leaderboards, and benchmark results across security CTF and hacking platforms

Semantic Observability for UNIX Systems - A lightweight C-based system prober with AI-powered analysis

B2B software vendor evaluation skill for Claude Code — domain-expert questions, vendor AI agent conversations, evidence-based scoring

Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain…

Automated framework for hijacking safety reasoning in large reasoning models via simulated reasoning traces and iterative prompt refinement to…

Security analysis tool identifying risks in Blackbox.ai extensions, including credential harvesting, unpatched CVEs, and privacy threats from hidden…

A prompt injection in a code‑review bot that executes AI‑generated fixes in a sandbox. The sandbox uses a blacklist to prevent dangerous commands,…

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution…

Detailed technical analysis of CVE-2024-5452, a remote code execution vulnerability in PyTorch Lightning via DeepDiff delta property pollution, with…

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

Orbit Tracer Security Agent for intelligent security remediation. Traces vulnerability blast radius using Orbit's knowledge graph, scores risk,…

AI-powered peer review for Pentest findings or Bug Bounty Reports — validates severity, evidence, and reporting quality before delivery using…

AI-enhanced vulnerability assessment and exploitation toolkit for modular scanning of web applications, detecting SQLi, XSS, RCE, CSRF, and more with…