ProjectTI

Consultor en Ciberseguridad.

[Stacy Schultz @StacySchulphks]

i'm sorry, Jev can WHAT?

it can take your website link, find people who need your product, email them and book the calls?

since when?? i've been doing this by hand for a YEAR.

ok. testing it: $30 free 👇

https://t.co/TsxFddXVJl

[Laurence Moroney 🇺🇸🇮🇪 🏴󠁧󠁢󠁷󠁬󠁳󠁿 @lmoroney]

Still running OCR over your PDFs before you can search them? Perplexity's new open embedding models are built to skip that step.

Perplexity released pplx-embed-v2-late on Hugging Face under the MIT license, in 0.6B and 9B sizes built on Qwen3.5. They're ColBERT-style late-interaction retrievers: every token gets its own 128-dimensional vector, and a query is scored by matching each of its tokens to the closest one in the document (MaxSim). They handle text, images, and rendered pages such as PDFs and slides. Both sizes share one embedding space, so the small model can query an index built with the 9B. On the image track of the public ViDoRe v3 benchmark, Perplexity reports nDCG@10 of 62.3% for the 0.6B and 65.2% for the 9B. Both were distilled from an internal 18B teacher.

Storing a vector for every token makes these indexes big, so test on your own data first. Index a few hundred of your pages with the 9B, compare results when you query with the 0.6B and the 9B, and note how much disk the index takes. 🔍 #RAG

https://t.co/usw06igZI7

[Oliver Prompts @oliviscusAI]

The entire RAG industry is about to get cooked.

Researchers developed a new RAG approach that bypasses almost everything traditional RAG depends on.

- No vector DB
- No data embeddings
- No chunking
- No similarity search

It's called PageIndex.

Instead of splitting your documents into chunks and loading them into Pinecone, it creates a tree index that lets the LLM reason through them like a human reading a book.

98.7% on FinanceBench. Outperforms every vector RAG on the leaderboard.

100% free. Open source.

[Co11ateral @co11ateral]

Web App Hacking with Cybermes

Cybermes works well for both pentests and bug bounty. It generates good reports and ships with a lot of built in skills

https://t.co/ZCaUagu2HY

[MAX @MAXdeg0]

THIS IS F**KING DANGEROUS

THE INTERNET IS LEAKING WAY MORE INFORMATION THAN MOST PEOPLE REALIZE.

I FOUND 3 OSINT TOOLS THAT CAN HELP YOU DIG DEEPER INTO WHAT’S ALREADY PUBLIC.

SHODAN IMAGES can surface screenshots from internet-connected devices that are publicly exposed.

GHOST-TRACK pulls together information from IP addresses, usernames, and phone numbers to help connect the dots.

Then there’s FLOWSINT — a visual OSINT workspace that lets you map relationships between people, websites, accounts, and other data points.

The scary part?

You don’t need to be inside the network to start finding useful information.

You just need to know where to look.

BOOKMARK this before someone take it down

LINKS BELOW

[0xor0ne @0xor0ne]

How to use LLMs for vulnerability research by @ZephrFish

MCP: https://t.co/MT4LbPOVGU
Harness: https://t.co/Boa1uD5BQu

#cybersecurity #llm

[Tom Dörr @tom_doerr]

Detects faces, maps landmarks, and compares identities within a private, on-premise Python SDK.

https://t.co/V7HnOlWLsP

[@kai_infra | IT Infrastructure Engineer @sideb_01]

WiresharkでHTTPS通信をキャプチャしても、
中身は暗号化されていて「Application Data」としか見えません。
しかし、TLS1.3でもClient側から鍵情報（Traffic Secretなど）を取得してWiresharkに読み込ませれば、HTTPS通信を復号してHTTPの内容を確認できます。

実際の手順をブログでまとめたので、興味があったら参考にしてください👇
https://t.co/R7IR0pQKfc

#Wireshark #Linux #インフラエンジニア #TLS

[TeddyCEO @TeddyinMedia]

GMAIL AUTOREG FOR $0

Found an open-source tool that automates the whole registration workflow.

Supports:

— 5sim / SMS-Activate / TextVerified / VirtualSMS
— multiple proxy setups
— account warming
— different registration modes
— configurable CAPTCHA + SMS providers

Repo:
https://t.co/6ZvghCKXUu

The setup is basically:

→ configure your providers / proxies
→ pick a registration mode
→ run it

Kinda wild that this is just sitting on GitHub.

Audit the repo before running it and use it only for accounts you’re actually allowed to create/manage.

[Co11ateral @co11ateral]

Katana

Finds hidden API, admin paths and parameters, which are often poorly secured. It's pretty common to see APIs that are not auth gated.

https://t.co/BEPdSHnSa5

[科技混子Chris @ChrisSlacker]

有人发布了一个完全越狱、开源、预构建的 iOS 26 虚拟机

仓库: https://t.co/X5N1tfJuBB

[7h3h4ckv157 @7h3h4ckv157]

AI Powered Passive Vulnerability Analysis for Burp Suite

• Intelligent
• Silent
• Adaptive
• Comprehensive

Resource: https://t.co/YI3c62qLhG

[Kat ⊷ the Poet Engineer @poetengineer__]

what if ai agentic coding be like:

[Fab @fabrice_mayrand]

This is the cheapest AI provider

Every model is discounted up to 81%!

ZDR is available

Try it -> https://t.co/Y77nstET9C

[Defileo🔮 @defileo]

THIS TOOL CLONES ANY WEBSITE WITH ONE COMMAND.

JCodesMore cloner app just hit 31,200 stars / https://t.co/hfFOVzBlKt

> Grabs every design token, colors, fonts, spacing, exact pixel values
> Screenshots and maps every section before writing a line of code
> Splits the rebuild across parallel AI agents working at once
> Outputs clean Next.js and Tailwind, nothing scraped or broken

Works with 10+ coding agents, best results with Claude Code

You give it a URL. It gives you back a codebase you can actually ship.

[阿西_出海 @axichuhai]

项目地址：https://t.co/5xJFRSPoAl

[Superman @thesupermannx]

https://t.co/3zeFhb7Zu3

[Nix0n @UnTalNixon_exe]

https://t.co/oibABigvVF

[rob. @robiartec]

Tu Windows está ejecutando más de 200 servicios en segundo plano ahora mismo.
La mayoría usan RAM, CPU y batería… y encima te espían.
Alguien se hartó de tanto bloat y creó la solución definitiva:

optimizerDuck
La herramienta gratuita que está volviendo locos a miles de usuarios de Windows

¿Qué hace exactamente?
> +35 optimizaciones de rendimiento, privacidad, batería y sistema
> Control total de más de 200 servicios (con etiquetas de riesgo claras)
> Eliminación de bloatware con vista previa antes de borrar
> Ajustes específicos y potentes para GPU AMD, NVIDIA e Intel

Lo que la hace diferente a todo lo demás:

Cada cambio genera automáticamente su propio archivo de restauración
Y te obliga a crear un punto de restauración antes de tocar nada.
Sin instalador.
Sin anuncios.
Sin telemetría.
Sin versión premium.
100% open source

Os dejo el repoo en los comentarios

[Shruti Codes @Shruti_0810]

GOODBYE TO CYBERSECURITY!

Someone just open-sourced an arsenal of AI hacking tools.

Not one.
Not ten.

Hundreds.

Inside the repository:

• Jailbreak frameworks for LLMs
• Prompt injection testing tools
• AI red team agents
• Model extraction utilities
• Supply chain attack demos
• Automated AI pentesting frameworks

These are the same categories of tools security researchers use to find vulnerabilities before attackers do.

Now anyone can study them.

That's both exciting... and terrifying.

The biggest threat to AI isn't smarter models.

It's insecure ones.

If you're building with LLMs and you're not actively testing your prompts, agents, and infrastructure—

You're probably shipping vulnerabilities you don't even know exist.

Open source is accelerating AI.

It's also accelerating AI attacks.

Repository link in the comments ↓