
Scanners-Box
A powerful and open-source toolkit for hackers and security automation - 安全行业从业者自研开源扫描器合辑

A powerful and open-source toolkit for hackers and security automation - 安全行业从业者自研开源扫描器合辑

AI-driven CLI for testing Android and iOS apps using natural language. Generates, runs, and fixes end-to-end tests on emulators/simulators with…

Desktop monitoring and local security reviews for AI agents, with opt-in policy-controlled execution and MCP action tools. Windows primary;…

The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers…

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging…

Agent-powered vulnerability scanner for large-scale codebases. Uses LLMs to find hard-to-detect security issues via regex matchers and AI…

A benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java).

An AI personal assistant with a focus on security.

An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE…

Self-hosted threat intelligence platform — feed aggregation, AI triage, MITRE ATT&CK coverage, and Sentinel-integrated detection engineering. Runs…

Kernel-enforced authority and runtime security for AI agents, autonomous systems, and general Linux workloads.

Proper sandboxing for agentic coding and web browsing

Research code for a gray-box trojan attack that flips a single KV-cache bit in fine-tuned LLM classifiers and measures per-class attack success rate.

AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models and the comprehensive MITRE ATT&CK…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord,…