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

Zero-trust agentic AI platform. Supports SaaS and OnPrem (airgapped) deployments.
The Ultimate Open-Source Security Arsenal for Hackers, Enterprises, and AI Agents——面向极客、企业与 AI 智能体的全域开源网络安全工具矩阵

Audit log and secret scanner for AI coding agents: see what Claude Code, Codex, Gemini CLI and 27 more ran on your machine, and find API keys leaked…

Let AI agents explore a running game from the inside. Live, safe, instant.

Pre-install security for AI agents, npm packages, and MCP servers. Zero-dep local static analysis; normal scans never execute package code.

Is 4-bit quantization more than noise to a chat model's safety behaviour? Code, pre-registration and labels.

openrisk is a tool that generates a risk score based on the results of a Nuclei scan.

100% Free & Open Source • Privacy-First Security Scanning and AI Code Review CLI

Curated collection of cybersecurity resources, labs, and training materials covering ethical hacking, penetration testing, exploit development,…

Windows network reconnaissance scanner with ping sweeps, TCP port scanning, and deep AI/ML service detection for finding shadow AI, rogue LLM…

Curated library of 78 offensive security SKILL.md modules that prime Claude with expert red team methodology across web, AD, wireless, cloud, and…

AI multi-agent autonomous penetration testing platform that runs recon, attack-surface discovery, exploitation validation and evidence-backed report…

Sec-Gemini is a cutting-edge AI model designed to enhance cybersecurity capabilities and empower defenders in the ongoing battle against cyber…

Benchmark harness that evaluates LLM agent tool-calling security under long-horizon tasks, generating prompt-injection and tool-poisoning attacks and…

Open-source gateway that secures, governs, and observes AI agents' MCP tool calls and LLM traffic, with API-key authentication and an admin console…

📡 Comprehensive collection of OSINT tools for cybersecurity professionals, researchers, and bug bounty hunters. Topics: information gathering,…

a guard that blocks catastrophic agent actions

On Loom, an approval rule named code_interpreter pauses the Strands tool and misses the ADK code and command tools. Empty, star, and…