Навыки: Безопасность

Risk management, CAPA protocol, human gate approval records, AI agent security controls, and periodic revalidation. Load...

This project focuses on benowin Blanc — parse Windows SDK/PHNT via libclang; struct layouts, enums, constants like dt wi...

This project focuses on integrate Ghidra's decompiler.

This project focuses on binary ninja cli for agents.

This project is CFB (Canadian Furious Beaver), a Windows kernel-mode IRP (I/O Request Packet) monitoring framework. It i...

This project focuses on linux SDK.

This project focuses on open/HarmonyOS abc file parser and decompiler.

This project focuses on refactored version of tokenext.

This project is a Windows kernel proof of concept for manually mapping a driver into a discarded section of a legitimate...

This project is a repository listed under cheat / game:csgo and centers on ec.

This project is a hardware ID spoofer for Windows that modifies disk, volume, NIC, ARP, SMBIOS, boot, and GPU identifier...

This project is the Kernel Driver Utility (KDU), a Windows tool for loading unsigned kernel drivers by exploiting vulner...

This project is kfd, a kernel-level file descriptor exploit framework for iOS/macOS that provides arbitrary kernel read/...

This project focuses on simple header only, kernel-mode alternative to lazy_importer.

This project is a Windows kernel utility or driver exploit tool. It provides kernel-level operations such as memory read...

A Windows kernel vulnerability controller that disables Driver Signature Enforcement (DSE) by patching CI.dll options vi...

This project focuses on blocking NMI interrupts.

This project provides guide-zh.

This project focuses on dIY Kernel.

This project is a modified QEMU fork from ISP RAS (Institute for System Programming of the Russian Academy of Sciences)...

Hex-Rays' Rust-based multi-architecture CPU emulator supporting x86, x64, ARM32, and AArch64 with JIT compilation, desig...

This project is a reverse-engineered SDK for a Source engine game (likely CS:GO) containing class definitions, interface...

This project is smap, a Windows kernel-mode shellcode mapper in C that loads position-independent shellcode into kernel...

This project focuses on smm cheat.

This project involves stack trace building or spoofing techniques for evading call stack analysis. It manipulates return...

STP (Simple Theorem Prover), a constraint solver for bitvector and array theories used in binary analysis, symbolic exec...

This project is a devirtualization engine for Themida.

This project is a reverse engineering analysis of Valve Anti-Cheat (VAC), documenting its internal detection modules, sc...

This project is VDK (Vulnerable Driver Kit), a collection of tools and libraries for exploiting vulnerable signed Window...

A cross-platform C/C++ memory access library providing unified read/write/module-enumeration APIs across multiple backen...

This project is a distributed snapshot-based fuzzer for Windows and experimental Linux targets. It combines coverage-gui...

This project is disassembler or debugger that works based on the extension plugin.

This project is a repository listed under anti cheat / encrypt variable and centers on xv.

This project is a repository listed under cheat / injection:android and centers on yaui.

Turns an AI video ad into a compliance report for TikTok Shop, TikTok ads, Meta, YouTube, the FTC, New York's synthetic-...

Review AI agent systems for agent impersonation, capability escalation, missing agent identity primitives, and authoriza...

Use when red-teaming an agentic AI / LLM application — indirect & zero-click prompt injection, MCP tool poisoning, persi...

Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.

Use when Claude Code permissions have accumulated in settings.local.json and you want to audit, consolidate, or clean up...

Review an AI system's audit logging for completeness, tamper-resistance, and regulatory readiness — covering what events...

Review AI-generated content pipelines for deepfake detection gaps, provenance chain failures, C2PA implementation correc...

Use when validating compliance, ownership, risk lifecycle, or framework integrity for regulated industries. Modes: compl...

Design and operate an organization's AI governance system: define governance principles, operating models and decision r...

Review an AI system for weak model version control, missing rollback plans, unsafe guardrail change workflows, inadequat...

Assess Model Context Protocol (MCP) servers and agent tool integrations — tool poisoning, prompt injection via tool desc...

Use when reviewing AI-generated, Vibe Coding, or agent-authored PRs, diffs, commits, or merge requests for fake logic, f...

Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vu...

Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agen...