CVE-2026-20687: AppleSEPKeyStore Use-After-Free — iOS/macOS kernel vulnerability (patched in 26.4)

WIP darksword kexploit implement

iOS <=26.0.1 DarkSword Kernel Exploit reimplemented in Objective-C

Role-Specific Evaluation of LLMs for Security Vulnerability Detection

Reverse-engineering reconstruction of the Coruna iOS exploit kit (iOS 16/17 chains)

DarkSword webkit exploit captured ITW

My personal directory of skills, straight from my .claude directory.

734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Works with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI & 20+ platform…

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

A cyber security toolkit blending manual testing with AI Agents

AI-powered bug bounty hunting from your terminal - recon, 20 vuln classes, autonomous hunting, and report generation. All inside Claude Code.

Claude Code skill to support Android app's reverse engineering

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

A plugin deobfuscate for IDA

A QEMU emulator for legacy Apple devices

A reverse-engineering agent for IDA Pro and Binary Ninja

hexrays pseudocode for every ios binary

MCP server that connects AI assistants to HackerOne for bug bounty hunting

🤹 Caido AI Skills

Advanced tweak configurator for iOS 10 and up

The leaked exploit toolkit for various iOS versions

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

Vulnerability detection framework by Binarly's REsearch team

A lightweight command sandbox for Linux, secure-by-default, built on Landlock.

AI-powered job search toolkit using Claude Code slash commands

A comprehensive guide to adversarial testing and security evaluation of AI systems, helping organizations identify vulnerabilities before attackers exploit them.

IDA Terminal

A Qt-based CyberChef interface designed for malware analysis workflows, particularly in IDA Pro

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.