I am a security enthusiast Secured @Google,@Microsoft etc | MSRC Q1 2022 top 50 | AI Security at Cisco
Metaverse!
Joined September 2019
- Tweets2.1K
- Following2.1K
- Followers3.4K
- Likes26.1K
Pinned Tweet
In this writeup! , I shared how I was able to ex filtrate data from airgaped computer which does not have internet , bluetooth , Wifi etc via camera status light and screenbrightness variation
medium.com/@harishhacker3010…
lolol! then first let LLMs to understand the code base of BLA and how it works then reverse via REA to avoid the trap lol
REA (reverse engineer anything) - F*CKED by chinese student...
solo dev just dropped protection for your app & site & game from reverse-engineering and AI hackers, for free
REA not dangerous anymore.
here's how to use and setup BLA (Blind LLM Agents):
first understand how it works:
• REA opens your app in 1 command, BLA hides traps inside it before you ship
• fake keys and decoy code for AI to chase, plus files built to blow past REA's own limits
• AI burns tokens on dead ends, your users get the exact same app
here's how to set it up for FREE:
1 → open Claude Code in the folder of your app, site or game
2 → say: " install Node.js 24 if I don't have it, build my project, then run npx bla-agents setup and npx bla-agents harden"
3 → it finds your build itself: dist, build, Electron .asar, .wasm, Python, native binaries
4 → it plants fake keys and decoy code, then checks every protected file still runs the same
5 → the step everyone skips: ship the files from the new .bla-hardened folder, not your old build
6 → for sites it protects the JS your site sends to browsers, your server code never leaves your server anyway
7 → want proof? run: npx bla-agents benchmark - before vs after on 14 test apps
paste link on repo below as soon as possible:
4
364
Lol 😂
The full run cost $1,213,430 in API credits—about $1,279 per distinct local privilege escalation vulnerability.
For context, applying historical Pwn2Own and TyphoonPWN bounty rates gives a hypothetical value of $18.9M–$66.3M.
This demonstrates the relative efficacy of using AI models for securing software—defenders should proactively analyze software to make cyber attacks cost-prohibitive.
4
3,954
We built an chrome extension which allows anyone to edit or add features to any website
github.com/harishsg993010/we…
1
4
413
This is amazing man
I built everything from scratch, 100% inhouse in india, it was just me & my obsession of making technology accessible to everyone in need!
It is a brain controlled robotic prosthetic hand!
Learn more at: brhm.in
200
I built a mini web browser for Agent in less than 10 hours using @Replit Agent last July
pypi.org/project/julia-brows…
Agent built using Julia browser called OpenAtlas outperformed @perplexity_ai Deep Research in Deep Reseach Bench
pypi.org/project/openatlas/
2
253
Browser Agents working on long context jobs are gonna prompt layoff of thousands people in service sector
1
147
Openpuffer is world’s fastest and fully opensource vectordb written in rust
Thanks @turbopuffer
Thanks @DhravyaShah this man posted about this go implementation couple of month back!
github.com/harishsg993010/op…
Meet OpenAtlas : CLI based browser Agent (not based on chromium and firefox)
pypi.org/project/openatlas
4
381
Help us stop North Korea’s fraudulent IT worker programs. These operations funnel funds into weapons development and violate international sanctions.
Got info? Contact us. You could be eligible for a reward and relocation.
home.treasury.gov/news/press…
1
262
I am building a SWE Agent which already has 19k downloads
I need an memory integration for it
@mem0ai vs @supermemory built by @DhravyaShah
Can you suggest which works well for code?
205