uid0

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

[uid0 @uidzero]

Most “AI pentesting” right now is theatre.

Cool demos. Zero outcomes.

So we built an OpenClaw agent, wired it with real skills + guardrails, and let it loose against:
• Production Active Directory
• A live web app

Result:
- 3 days of AD recon → 3 hours
- 23 valid findings in AD
- 52 valid findings in Web app
- Valid attack paths toward DA

We’ve open-sourced how we did it, example skills, infra, and the agent persona:

https://t.co/4xfVpARTyc

This is what AI pentesting looks like when it’s not a demo.

[uid0 @uidzero]

@HackingLZ Have you got access to daybreak red yet? Not had one refusal, almost like it has no guardrails whatsoever!

[uid0 @uidzero]

@UK_Daniel_Card Only 13??? 🤣

[uid0 @uidzero]

@HackingLZ Want to know something funny, we hit guardrails and AUP multiple times with Mythos too, while doing the work it was INTENDED to do 🤣

[uid0 @uidzero]

@blackroomsec @IceSolst Hah, mythos is not as powerful as they as people have been led to believe. I can't speak about it too much but I have extensive time with Mythos now and other than vulnerability hunting, it's a shitter when it comes to actual "hacking" or adversarial work.

[uid0 @uidzero]

@UK_Daniel_Card Oh something I forgot to mention earlier when we were talking about this dude. Let's not forget that OpenAI are about to IPO 😉

[uid0 @uidzero]

@rekdt @IceSolst Lol, forgot about that douchebag, what a gem to keep in the archives 🤣

[uid0 @uidzero]

@whenismattlive I've used stickerapp in the past. Price wise it really depends what stickers you are after, if I remember rightly it was 40 quid for 100 die-cut ones

[uid0 @uidzero]

@ClownYouAllDay @UK_Daniel_Card This is how I work already. I tend to plan out and crate an MVP with one model, then parse it through another/or more for sanity checking and suggested additions.

[uid0 @uidzero]

@UK_Daniel_Card Watch this space, more AI content inbound 🙃

[uid0 @uidzero]

@UK_Daniel_Card @GsInfosystems This is actually a good idea, added to the list

[mRr3b00t @UK_Daniel_Card]

ok tweeps, we are GO GO GO! we have a shit load of LLM generated learning content! LOL

don't worry, it's not going to be SLOPPY! (well not too Sloppy) I've got my good friend @uidzero roped into this game now!

We will make sure it's not shit! (i didn't say amazing, just not SHIT) :P

[uid0 @uidzero]

@OHS1327 Appreciate it. Watch this space, we might have some more skills and further AI antics we've been working on dropping in the near future 🙃

[uid0 @uidzero]

Most “AI pentesting” right now is theatre.

Cool demos. Zero outcomes.

So we built an OpenClaw agent, wired it with real skills + guardrails, and let it loose against:
• Production Active Directory
• A live web app

Result:
- 3 days of AD recon → 3 hours
- 23 valid findings in AD
- 52 valid findings in Web app
- Valid attack paths toward DA

We’ve open-sourced how we did it, example skills, infra, and the agent persona:

https://t.co/4xfVpARTyc

This is what AI pentesting looks like when it’s not a demo.

[uid0 @uidzero]

One API call > allow / warn / flag / block. Drop it in front of any LLM app or agent.

Built by someone who attacks these systems, for the people defending them.

RootSignal Warden is cooking!!

(more to come soon - watch this space) 👀

[uid0 @uidzero]

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 ⏬️🧵

[uid0 @uidzero]

And it doesn't cry wolf....

~0.98 precision on real benign traffic. It knows the difference between an attack and someone just talking about one.

You update it like threat intel; add a rule, not retrain a model.

[uid0 @uidzero]

We let openclaw loose in our prod AD network..

Relevant persona, skill, architecture and report made public.

Check out how we achieved this in the Sophos blog post below.

https://t.co/VwitSEmArx