usar claude opus 4.8 GRATIS sin tarjeta y sin límites 😳
la prueba business de notion (30 días) te da opus 4.8 ilimitado dentro de notion AI
tarda 8 min en configurarse
lo que incluye el trial:
•opus 4.8 sin límite de mensajes
•acceso a GPT-5.5 y gemini
•agentes de notion 24/7
•modo research
•notas de reuniones
•agentes personalizados
guía paso a paso (trial business gratis):
1.consigue un email nuevo
crea un gmail que nunca hayas usado en notion
2.regístrate en notion
abre una ventana de incógnito, ve a notion. so, click en sign up, verifica tu email nuevo
3.crea tu workspace
click en “create workspace”, ponle el nombre que sea
4.activa el trial business
en la pantalla de planes elige “Business”, click en “try for 30 days” — sin tarjeta, aparece el badge de trial en la sidebar
5.usa opus 4.8
click en notion AI en la sidebar, click en el selector de modelo abajo del chat, selecciona opus 4.8, prompea sin límites
si ya tienes notion: salta directo al paso 5
cuando se acaben los 30 días te pide pagar o bajar de plan → repite con otro email para 30 días más
la forma más barata de usar opus 4.8 ahora mismo
guárdalo antes de que cierren el trial
13 Original OAuth Attack Techniques
OAuth is the login layer of the modern web.
Every "Continue with Google." Every "Sign in with GitHub." Every SSO button on every SaaS you've ever tested. All OAuth under the hood.
Most implementations are broken in ways that aren't documented anywhere.
Here's one of 13 original techniques — Grant Type Substitution → MFA Bypass.
MFA bound to the browser flow only. Switch grant type, MFA disappears. CVE-2024-37893.
The password grant being present is itself a finding worth reporting.
MCP is OAuth now and nobody is testing it.
Full breakdown in the replies.
C̶l̶a̶u̶d̶e̶ ̶B̶u̶g̶ ̶H̶u̶n̶t̶e̶r̶ is now BUG HUNTER.
We changed the name because it is no longer limited to Claude Code.
Now it is a standalone open-source CLI that runs from any terminal.
Use Ollama, Groq, DeepSeek, Claude, OpenAI or Grok.
Built for the bug bounty community.
Run it locally with Ollama - no paid AI subscription required.
We are very close to 2.5K GitHub stars. Let’s make it happen, guys.
More updates coming soon.
#OpenSource #BugBounty #CyberSecurity #AI #EthicalHacking #Ollama #GitHub #SecurityTools #BugHunter
Holy sht.. Hackers are going to love this.
Someone open sourced an all-in-one hacking toolkit that bundles every major pentesting tool into a Single CLI menu.
You install it once and get instant access to tools across every category from anonymity, info gathering, wireless attacks, password cracking, web scanning, exploit frameworks, payload GENERATION, and more.
It's called HackingTool.
→ One menu launches Tor, Anonsurf, Macchanger, and proxy chains in seconds
→ Bundles Nmap, Dracnmap, RED HAWK, and ReconSpider for full network recon
→ Ships SQLMap, XSStrike, WPScan, and SecretFinder for web exploitation
→ Includes John the Ripper, Hashbuster, and BruteX for password attacks
51K stars. Runs on any Linux distro.
100% open source.
‼️ Lancement de notre Projet - NEXUS_OSINT V1
🌐Une plateforme dédiée à la visualisation et à l'analyse de données en sources ouvertes intégrant :
• 🌍 Cartographie interactive Mondiale
• 📡 Flux OSINT géolocalisés
• 🎥 Live Cams synchronisées
• ⏪ Frise temporelle avancée
• ✏️ Outils d'analyse intégrés
💻Les visuels ci-dessous présentent de manière simplifiée les principales fonctionnalités de la plateforme.
👉 Disponible maintenant : https://t.co/vWqIUg0wxv
A scientist in Denmark figured out how to make Claude prepare his job applications. He open-sourced the whole thing.
His name is Mads Lorentzen. He is a PhD geophysicist. He built it on top of Claude Code and released it under MIT license.
Here is what it does. You fork the repo, fill in your background once, and it runs a five-step pipeline for every job you want to apply to.
Step 1. It reads the job posting and scores how well you fit.
Step 2. It drafts a tailored CV in LaTeX, picking only the experience that matches.
Step 3. It writes a cover letter framed around what you would bring to the role.
Step 4. A second AI agent reviews the first agent's work, points out weaknesses, and the first agent revises.
Step 5. It compiles both into clean PDFs you can send.
The whole thing is a folder of markdown files. The candidate profile, the writing style rules, the CV templates, the interview prep notes. Every step is plain text you can read and change.
The job portal search is built for Danish boards. The application workflow itself works for any country.
489 stars. 270 forks. A fork-to-star ratio that high means people are using it, not only bookmarking.
Mads is not a startup founder. He built this because he needed it for himself, then shared it.
This is the future of job hunting. Not a service you pay for. A workflow you own.
(Link in the comments)
Korea’s #1-ranked hacker on HackerOne is back with a follow-up post! 👀
Hyunseo Shin (KU, 4th year) previously shared how he uncovered open-source 0-days using LLM agents.
Now, he breaks down the AI-based vulnerability detection workflow behind those findings.
Full post below 🔥
🔗 https://t.co/6UodzgY5tN
#CyKor #AI #hackerone
If you’re not using https://t.co/QzZGLOjipz for your bug bounty hunting, you’re probably leaving money on the table 💸
A lot of impactful vulnerabilities (SSRF, Host Header Injection, Blind XXE, Webhooks, async callbacks…) need reliable OOB interaction detection.
https://t.co/QzZGLOjipz gives you that for free. 👀
#BugBounty #AppSec #CyberSecurity #Hacking #Pentest #BugBountyTips
The 10 fastest growing GitHub repos this week:
1. codegraph (+14.1K stars)
Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, OpenCode, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
https://t.co/PmnpMlGC3r
2. openhuman (+17.1K stars)
Your Personal AI super intelligence. Private, Simple and extremely powerful.
https://t.co/mrpvMxUFwe
3. academic-research-skills (+11.6K stars)
Academic Research Skills for Claude Code: research → write → review → revise → finalize
https://t.co/dek8R1gZIu
4. RuView (+6.8K stars)
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
https://t.co/UILhiVpLyX
5. agentmemory (+6.9K stars)
#1 Persistent memory for AI coding agents based on real-world benchmarks
https://t.co/KttGKncznV
6. supertonic (+3.6K stars)
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
https://t.co/LA0oJzR5Hf
7. CloakBrowser (+7.0K stars)
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.
https://t.co/smRQh0wY3u
8. ViMax (+2.7K stars)
"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
https://t.co/Jp53BzC0rK
9. 12-factor-agents (+1.9K stars)
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
https://t.co/qMqRwXa7iu
10. bun (+2.0K stars)
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
https://t.co/UAtNVbQlBd
The theme this week: agent memory, context efficiency, and on-device intelligence are making AI infrastructure the hottest build category.
Bookmark this. Next week's list will look completely different.
هناك العديد من الأكواد السرية (غير الرسمية) التي يكتشفها مستخدمو نموذج كلود وخبراء الذكاء الاصطناعي باستمرار ويشاركونها عبر منصات التواصل الاجتماعي، وهي أكواد تستفيد من أسلوب البرمجة والتدريب في النموذج.. فعندما يرى النموذج النصوص المكتوبة بعينها بالطريقة ذاتها يغير مباشرة طريقة استجابته للأوامر وتقديم إجابات أفضل وأكثر جودة.. فما أبرز تلك الأكواد؟
Introducing a 100% free coding agent with DeepSeek v4 Pro
Choose any model, all free:
- DeepSeek v4 Pro/Flash
- Kimi K2.6
- MiniMax M2.7
npm i -g freebuff
RentAHuman -- the platform where "AI Agents" hire real humans for physical tasks - leaked its entire user database.
187,714 personal emails (at the time), all it took was few minutes, some tokens and one Claude Code command.
Here's how my AI attacker found it 🧵
Pure Rust + Candle + alloy‑rs. Ready for MI300X inference as soon as AMD Cloud credits are activated.
Building the safest AI pipeline on AMD ROCm. 🚀
#AMDDevHack@lablabai@AIatAMD