Hasbullah Marwan

Autonomous vulnerability research with Claude Code + MCP blog.zsec.uk/bullyingllms/ #infosec #llm

AutoPentestX — Automated Penetration Testing Toolkit 💀🔥 Automates recon, scanning, and vulnerability assessment workflows from a single toolkit. Built for faster security testing and repeatable assessments. github.com/Gowtham-Darkse… #Pentesting #CyberSecurity #Infosec

𝗦𝗵𝗮𝗻𝗻𝗼𝗻 — 𝗔𝗜 𝗪𝗵𝗶𝘁𝗲-𝗕𝗼𝘅 𝗣𝗲𝗻𝘁𝗲𝘀𝘁𝗲𝗿 💀🔥 • Analyzes source code + runs real exploits • Targets web apps & APIs • Detects: Injection, XSS, SSRF, Auth/Authz • Reports only working PoC vulnerabilities • Autonomous: recon → exploit → report • Uses browser automation + CLI tools • Handles login, 2FA, sessions • White-box testing (needs source code) • Supports CI/CD workflows ⚠️ Active exploitation tool → use with permission only github.com/KeygraphHQ/sha… #CyberSecurity #Pentesting #AppSec

Awalnya gua kira nonton short video di HP itu bisa menjadi pengisi waktu luang. Tapi setelah baca jurnal ini, gua baru tau efeknya bisa berbahaya untuk otak. Penelitian dari Tiongkok ini meneliti 48 orang, terus dilihat kebiasaan mereka nonton short video, lalu dicek fungsi atensi & kontrol diri, didukung juga dengan pemeriksaan EEG. Hasil penelitian ini cukup bikin gue kaget antara lain: -Semakin sering nonton short video, semakin turun kemampuan otak buat kontrol diri -Fungsi eksekutif otak, terutama atensi, juga menurun Short video ternyata berasosiasi dengan overstimulasi dengan karakteristik cepat, singkat, dan penuh reward instan. Lama-lama otak jadi kebiasaan butuh stimulus cepat, sehingga bikin fokus jangka panjang makin susah. Yang menarik dari studi ini adalah: Semakin tinggi tingkat kecanduan (adiksi) untuk menonton short video di smartphone, berasosiasi dengan semakin rendah tingkat pengendalian diri (self control) 𝗞𝗘𝗦𝗜𝗠𝗣𝗨𝗟𝗔𝗡 Kebiasaan nonton short video ternyata berkaitan dengan penurunan self-control dan turunnya fungsi eksekutif otak, terutama kemampuan atensi.

Are you worried about your government or foreign governments eavesdropping on your data or conversations? Now you can build your own private, low-cost, cellular network! Build Your Own Low-Cost, Private Cellular Network Exclusively from Hackers-Arise! June 9-11 Part of our Subscriber Pro and Signals Intelligence packages. hackersarise.thinkific.com/bundles/sdr-si…

Sekarang udah nggak butuh les bahasa Inggris berbayar puluhan juta. Claude bisa jadi guru bahasa Inggris kalian yang available 24 jam, dan 100% gratis. Gue kasih tau cara pakainya + 7 prompt gratis. Jangan lupa di-save 🧵

Someone just dropped a 9-layer production AI architecture and it's the most honest breakdown I've seen. services/ - RAG pipeline, semantic cache, memory, query rewriter, router. Not one file. Five. agents/ - document grader, decomposer, adaptive router. Self-correcting by design. prompts/ - versioned, typed, registered. Never hardcoded. security/ - input, content, output. Three guards not one. evaluation/ - golden dataset, offline eval, online monitor. Most people skip this entire layer and ship blind. observability/ - per-stage tracing, feedback linked to traces, cost per query. .claude/ - agent context so your AI coding assistant knows the codebase before it touches a file. The demo is one file. Production is this.

Teori ending One Piece yg masih saya percaya sejak 10thn lalu berasal dari buku ini, dari Rokushikimaster. Ending cerita One Piece belum lari dari teori di buku ini.

Free games Claim it store.steampowered.com/app/613100/Hou…

i told Claude to scan every Polymarket wallet and GitHub repo woke up to +$3,582. the terminal was still running on my screen. it analyzed thousands of wallets overnight. most of them bleed money. but 340 had something different - asymmetric payouts. entering at 27 cents. exiting at 91. losing 27 cents when wrong. winning 64 when right. you only need to be right 1 in 4 times. they were right half. Claude found 3 patterns: category specialists - one wallet: 91% wr on crypto. 14% on politics. total looks average. filter to crypto only - top performer. speed arbitrage - 47 wallets entering 3-8 seconds after Binance moved. before Polymarket updated. not predicting. just faster. near-zero accumulation - buying at 2-8 cents weeks before resolution. $8 in, $200 out. hundreds of times. it connected GitHub repos to run all three: > poly_data - scanned every wallet and entry price. > polyterm - whale tracking and insider detection. > py-clob - placed the orders. 7 wallets copied. 204 trades. $25 seed. +$3,582. 6 agents running: > sigma_decay - 78% conviction > darkpool_7 - 87% > velvet_void - 85% > profitprinter - 54% the equity curve tells the whole story. $25 to $3,582 without a single dip worth mentioning. sharpe 2.09. copytrade here: @1743116" target="_blank" rel="nofollow noopener">kreo.app/@1743116 87% of Polymarket is exit liquidity. the question is which side you're on.

COURSE CLAUDE 1 JAM FULL GRATIS!! Orang ini ngebawain course Claude 1 jam gratis dalam bahasa Inggris tapi udah gua kasih subtitle Bahasa Indonesianya juga Buat kalian yang mau belajar Claude dan gamau ribet, nih udah gua sediain. Isinya itu gimana bisa bikin Claude otomatisasi kerjaan kita sehari-hari Tonton aja videonya dibawah sini 👇👇, inget ditonton jangan di bookmarks doang ya wkwk Shoutout to @JulianGoldieSEO for making this video, I'll translate it to Indonesian, so that people in Indonesian also can watch and study Claude.

[Download 585-page PDF eBook] Game Theory: arxiv.org/abs/1512.06808 ————— #GameTheory #Gamification #Mathematics #Statistics #Probability

Meet the Cybersecurity Baron: a specialized LLM fine-tuned for offensive security. This isn't your average chatbot. It's a quantized, 6-bit GGUF model built on Llama 3.1 Instruct, designed to think like a penetration tester. Perfect for ethical hackers and security researchers.

🚨 BREAKING: Someone just open-sourced your own personal intelligence terminal. It's called Crucix. Bookmark it for later. It watches 27 live data feeds across the entire planet and alerts you when something changes. Governments and intelligence firms pay six figures for this kind of setup. This runs on your laptop for free. No cloud. No subscriptions. No telemetry. Just a single Node.js server and a Jarvis-style dashboard. What it watches every 15 minutes: → ACLED for armed conflict events worldwide → Federal Reserve economic indicators via FRED → OFAC + OpenSanctions for sanctions screening → 17 curated Telegram intelligence channels for social sentiment → Maritime AIS for vessel tracking and sanctions evasion detection → GDELT for global event tracking across 100+ languages → WHO for disease outbreak alerts → ReliefWeb for UN humanitarian data → CelesTrak for satellite constellation tracking: ISS, Starlink, OneWeb → VIX and credit spread risk gauges Every sweep computes what changed, what escalated, and what de-escalated since the last cycle. Hook up an LLM (Claude, GPT, Gemini), and it generates trade ideas based on cross-domain signal correlation. Without an LLM, a deterministic rule engine still evaluates everything. 18+ sources work with zero API keys. No setup friction. 100% Open Source. MIT License. (Link in the comments)

@elonmusk What happens when the straight of Hormuz closes.

Open Source Intelligence (OSINT): Gathering Information on a WhatsApp Account In this article, we will delve into how to utilize the WhatsApp-OSINT tool for extracting profile account details during OSINT investigations: hackers-arise.com/open-source-in… @three_cube @DI0256 @co11ateral

For those of you interested in OSINT, here is another tool for WhatsApp hackers-arise.com/open-source-in… @three_cube @_aircorridor #osint #privacy

🛡️ Kali Linux Enhances AI-driven Penetration Testing with Local Ollama, 5ire, and MCP Kali Server Source: cybersecuritynews.com/kali-linux-ai-… The Kali Linux team has published a new entry in its growing LLM-driven security series, this time eliminating all reliance on third-party cloud services by running large language models entirely on local hardware. The guide demonstrates how security professionals can use natural language to drive penetration testing tools, all processed on-premise, with no data leaving the machine. The full-stack Ollama, mcp-kali-server, and 5ire are open source, hardware-dependent rather than service-dependent, and tunable based on available VRAM. #cybersecuritynews #kali

Just added something crazy to the OpenClaw 3D office. You can now see the agent’s computer screen and watch what it’s doing in “real time”. Feels like looking over your AI employee’s shoulder.