uid0 (@uidzero) header
uid0 (@uidzero) profile picture

Red Team @ Sophos | Offensive security, Pentesting, LLMs, agents & GenAi

Joined February 2014
Everyone's "AI Guardrail" is just a second LLM grading the first ones homework. I'm a senior red teamer - I break these systems for a living. So, I'm building the opposite. Meet RootSignal Warden A thread ⏬️🧵
1
1
1
10
384
Just came across this on good old LinkedIn, by a senior security program manager.. do these people really believe we run ZAP and metasploit during pentests? 🤣🤦🏻‍♂️ mindblown
1
2
162
Replying to @HackingDave @_xpn_
Love this, it definitely works been doing it for years. Although you just lost a friend point as I spat out my correctly boiled from a kettle tea over that comment 🤣
1
53
I reposted this earlier today but wanted to reflect. This manifesto played a huge part in me getting into the hacking culture, coupled with stories like reading the about MIT hacking PDPs, Lopht, CDC, Cptn Crunch, Mitnick to name a few A thread 🧵
1
1
154
Replying to @UK_Daniel_Card
See ya there buddy
1
1
49
So, that's just the start of digging into this. Im going to pick this back up later with some other applications that I have concerns with, starting with the good old Roblox!
1
1
146
So ive noticed that my posts are falling out of the thread for the android parental controls stuff. Thread is pinned to my profile for anyone that wants to read in order!
1
123
Let's take another angle, the youtube parental controls are somewhat bad. Let's type for example "how to kill someone" Whatttttt?!?!?!?!?! Yep that looks inappropriate!
113