A command-line tool that searches for usernames across 400+ social networks and platforms to help investigators and security researchers track down social media accounts. Useful for OSINT investigations, cybersecurity research, and digital forensics.

An autonomous AI pentester that analyzes web application source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before production deployment. It performs white-box security testing with actual proof-of-concept attacks rather than just theoretical vulnerability scanning.

A Claude Code skill that decompiles Android APK/XAPK/JAR/AAR files and extracts HTTP APIs, Retrofit endpoints, and authentication patterns from apps without source code. Helps security researchers and developers analyze app structure and trace API call flows through obfuscated code.

An open-source comprehensive vulnerability scanner that leverages community-driven security intelligence and automated penetration testing capabilities. Features real-time health monitoring, centralized logging, and Docker-based deployment for enterprise-grade security scanning.

Meta's set of trust-and-safety tools for assessing and improving LLM security — code-scanning, jailbreak benchmarks, and input/output classifiers.

Split your file into encrypted fragments so you don't need to remember a passcode — distribute the pieces; any threshold reconstructs the original.

Security firewall for AI agents — guardrails against prompt injection and dangerous tool calls. By Deno.

Microsoft's open-source framework for detecting, redacting, masking, and anonymizing PII in text and images.

An AI-powered autonomous red team framework that automates the complete offensive security pipeline from reconnaissance to exploitation to post-exploitation, then automatically triages findings, implements code fixes, and opens GitHub pull requests for remediation.

Advanced DNS tunneling VPN that bypasses internet censorship by disguising traffic as normal DNS queries. Optimized for stability in harsh network conditions with multi-resolver support and adaptive routing.

NVIDIA's LLM vulnerability scanner — probes models for jailbreaks, prompt injection, data leaks, hallucinations, and toxicity at scale.

A comprehensive curated list of AI security resources including frameworks, standards, offensive and defensive tools, learning materials, and open source security tools. Essential for security professionals working with AI systems and machine learning.

Anthropic's GitHub Action that uses Claude to analyze diffs for security vulnerabilities — flags issues with explanation and fix suggestions on every PR.

AI agent security scanner that detects vulnerabilities in agent configurations, MCP servers, and tool permissions. Ships as a CLI, GitHub Action, and GitHub App.

A collaborative intelligence platform that provides geopolitical analysis, cybersecurity threat intelligence, and emerging risk assessments. Connects AI analysts to track and analyze global events across domains like geopolitics, cybersecurity, energy, and finance.

Real-time geospatial intelligence platform that aggregates 60+ OSINT feeds into a unified dark-ops interface. Track aircraft, ships, satellites, CCTV cameras, GPS jamming, and global events with AI agent integration and decentralized communications.

An OSINT search engine that allows users to discover and map real-world infrastructure using OpenStreetMap data. It provides intelligence gathering capabilities for analyzing physical locations and infrastructure patterns.

One-command CLI to patch CVE-2025-66478 (React 2 Shell RCE) in Next.js and React Server Components apps.

OpenAI's collection of security automation bots: triage, analysis, and response workflows powered by LLMs.

Patched web vault builds for Vaultwarden, the unofficial Bitwarden-compatible self-hosted password server.

End-to-end security platform for OpenClaw AI agents that provides audit checks, automated hardening, and runtime protection against prompt injection, credential theft, and privacy leaks. Features 56 audit checks, 15 behavioral rules, and comprehensive OWASP ASI framework coverage.

Reference implementation of CaMeL, a design-time defense system against LLM prompt injection attacks.

A Bluetooth Low Energy (BLE) scanner that can discover nearby devices, track specific devices by MAC address, and resolve privacy-randomized addresses using Identity Resolving Keys (IRKs). Features multiple scanning modes, RSSI filtering, distance estimation, and both terminal and web GUI interfaces.

CLI that checks if your installed Node.js version has any known security vulnerabilities.

Security toolkit for AI agents — scan for dangerous skills and MCP configs, test prompt injection resistance, audit live MCP servers for tool poisoning.

ClawShell provides Linux-style permissions for AI agent secrets, treating agent execution as adversarial compute to protect sensitive data. It's a security layer designed specifically for AI agents written in Rust.

A privacy-focused routing tool that helps users plan routes while avoiding Flock safety cameras and ALPR surveillance systems. Maps over 90,000 surveillance cameras across the United States to create privacy-first navigation paths.

Quantum-resistant DAG-based anonymous communication protocol, built end-to-end with Claude Code via a TDD implementation plan.

Rotate IPv6 addresses for specific subnets to unblock IPv6-enabled sites (Google by default, customizable for others).

TypeScript markdown sanitizers for safer AI-agent output — defend against prompt injection in rendered responses.