AI Tools Radar › Categories › Security & sandboxing
AI security, pentesting & agent sandboxing tools
AI security tools, penetration testing, reverse engineering, sandboxes for agents, prompt-injection and jailbreak research. 33 items in today's radar (data fetched 21 Oct 2026, 14:13 (Berlin time)). Categories are assigned by fixed keyword rules on GitHub topics, repo names, descriptions and Show HN titles; an item can be in several categories. How categories work.
All 393Agents & automation 196Coding assistants & dev tools 168Chat apps & assistants 28LLM inference & serving 36RAG & search 28Training & fine-tuning 11Models & research 36Image, video & audio generation 52Voice & speech 21Computer vision 8MCP, skills & plugins 146Evaluation & observability 22Data & datasets 30Local / on-device AI 45Security & sandboxing 33Learning & resources 48Other 16
Trending on GitHub today (4)
| Repository | Stars today | Total stars | Language | License | Created |
|---|---|---|---|---|---|
| 1. cloudflare/security-audit-skill A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings | 1,712 | 35,084 | JavaScript | MIT | 2026-06-18 |
| 2. Asymptote-Labs/agent-beacon The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu | 447 | 2,296 | Go | MIT | 2026-05-12 |
| 3. usestrix/strix Open-source AI penetration testing tool to find and fix your app’s vulnerabilities. | 393 | 70,627 | Python | Apache-2.0 | 2025-08-05 |
| 4. trycua/cua Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation. | 208 | 30,514 | Rust | MIT | 2025-01-31 |
Trending on GitHub this week (5)
| Repository | Stars this week | Total stars | Language | License | Created |
|---|---|---|---|---|---|
| 1. morluto/rea Reverse engineer anything with agents, from app behavior down to native binaries. | 157,631 | 353,473 | TypeScript | MIT | 2026-04-14 |
| 2. vxcontrol/pentagi Fully autonomous AI Agents system capable of performing complex penetration testing tasks | 3,666 | 31,670 | Go | MIT | 2025-01-06 |
| 3. mksglu/context-mode Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks. | 3,556 | 31,553 | TypeScript | Other | 2026-02-23 |
| 4. elie222/rakazo Open-source Grok Bot alternative. Choose your own model and sandbox. | 1,052 | 5,023 | TypeScript | Apache-2.0 | 2026-08-13 |
| 5. gitleaks/gitleaks Find secrets with Gitleaks 🔑 | 278 | 30,185 | Go | MIT | 2018-01-27 |
New repos of the last 30 days (21)
| Repository | Age | Total stars | Language | License | Created |
|---|---|---|---|---|---|
| 1. rehan-remade/universal-modder Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos. | 21 d | 8,592 | Python | MIT | 2026-09-30 |
| 2. Jakeschincariol/replica-skill Eleven free Claude skills that clone any app: reverse-engineer it, rebuild it, test it for bugs, then fix what its users hate. Free, MIT. | 18 d | 3,888 | Python | MIT | 2026-10-03 |
| 3. onehumanbeing/esp32-iphone-agent Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak. | 9 d | 3,457 | C | MIT | 2026-10-11 |
| 4. jiwoochris/artex-global ARTEX 한국어판 · AI 자율 침투 테스트 프레임워크(upstream: Autumn-27/ARTEX, AGPL-3.0) | 17 d | 1,878 | Go | AGPL-3.0 | 2026-10-03 |
| 5. perplexityai/SPACE Sandboxed Platform for Agentic Code Execution: pluggable-runtime sandboxes for running agent and user code in isolation. | 19 d | 1,771 | Rust | Apache-2.0 | 2026-10-01 |
| 6. angusdevgo/Seep-Reverse-Lab Agent-Native multi-platform reverse engineering and CWE-602 client-side authorization audit workbench. | 27 d | 1,760 | Lua | GPL-3.0 | 2026-09-23 |
| 7. trhhubsd/ARTEX ARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI 自主渗透测试系统 · 百度 agent+ 攻防挑战赛冠军 | 12 d | 1,526 | Go | AGPL-3.0 | 2026-10-08 |
| 8. morluto/awesome-reverse-engineering Curated reverse-engineering tools and learning resources for binaries, apps, firmware, formats, and protocols. | 11 d | 1,038 | Python | CC0-1.0 | 2026-10-09 |
| 9. Zfinix/eleven Agent-first reverse engineering for macOS, Windows and Linux: any ACP agent reads, renames and patches binaries, Android apps and GPU kernels next to you. | 7 d | 816 | TypeScript | Apache-2.0 | 2026-10-13 |
| 10. openqodex/openqodex Open source code review that runs in your coding agent before you push. Scanners plus a separate AI reviewer, on your own login, no key. | 19 d | 781 | TypeScript | Apache-2.0 | 2026-10-02 |
| 11. zhuyansen/awesome-claude-video-skills Open-source skills and toolkits that let Claude Code, Codex and other coding agents make video. 180 repos by type, each security-graded. English / 中文. | 24 d | 779 | – | Other | 2026-09-27 |
| 12. nealbridges/VulnHunter Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebuilt for any agent harness. | 28 d | 766 | Python | Apache-2.0 | 2026-09-22 |
| 13. graygnatconsole/mcp-audit-tool 🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready. | 25 d | 552 | Python | MIT | 2026-09-26 |
| 14. qybaihe/mu mu (μ): a coding agent that thinks before it acts. A small, fast judge makes the routine calls, the big model does the work. Built on pi and AionUi. | 29 d | 532 | TypeScript | MIT | 2026-09-22 |
| 15. i12bp8/decomp.wtf archived What The Function: your AI agent decompiles games you own into C that compiles to the exact same bytes. Runs locally. | 8 d | 531 | Python | MIT | 2026-10-13 |
| 16. strands-agents/box Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon, with Linux support planned. | 18 d | 449 | Rust | Apache-2.0 | 2026-10-02 |
| 17. alexgaoth/awesome-reverse-engineered Don't reverse engineer it twice. 12,000+ open-source tools built by reverse engineering closed apps, APIs, devices, protocols, file formats, games and AI tools. Search site + agent skill, refreshed nightly. | 9 d | 356 | Python | MIT | 2026-10-11 |
| 18. scaleapi/agentenv-framework Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now. | 26 d | 350 | Python | Apache-2.0 | 2026-09-24 |
| 19. songshikang0111/awesome-REA-cases A curated collection of REA and AI-assisted reverse engineering cases, projects, and ideas. Updated every four hours. | 9 d | 300 | Python | MIT | 2026-10-12 |
| 20. heaven999b/hello-agent-system 👋 Hello Agent System — learn enterprise AI agent system design by building every production layer from scratch. 17 bilingual lessons (EN/中文) with tested exercises: tools, architectures, reliability, security, evals, distributed execution, cost, RAG, release ops. 企业级 Agent 系统设计训练营 | 24 d | 276 | Python | MIT | 2026-09-27 |
| 21. dagoSte/squadra Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits. | 23 d | 266 | Python | MIT | 2026-09-28 |
AI launches on Show HN (3)
| Show HN post | Points | Comments | Posted |
|---|---|---|---|
| 1. Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server HN discussion · by edverma2 | 121 | 46 | 2026-10-02 |
| 2. Show HN: Corral – Kill every command your agent starts HN discussion · by CG144 | 19 | 6 | 2026-09-29 |
| 3. Show HN: Plimsoll, a self-hosted sandbox for code your AI agent writes HN discussion · by cagster | 16 | 3 | 2026-10-11 |