Red Team @ Sophos | Offensive security, Pentesting, LLMs, agents & GenAi
Joined February 2014
- Tweets1.2K
- Following1.9K
- Followers1.7K
- Likes7.5K
Pinned Tweet
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:
github.com/sophos/pentesting…
This is what AI pentesting looks like when it’s not a demo.
uid0 retweeted
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
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.
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.
sophos.com/en-us/blog/we-let…
If your interested in the methodology behind penetration testing AI ecosystems, check out my latest blog post!
Deep dives on these methodologies to follow soon!
#cybersecurity #ai #hacking #ethicalhacking #offensivesecurity
blog.rootsignal.co.uk/blog/p…
Most companies think the risk with AI is the model. Its not....
If an attacker can influence the model, they can influence the systems behind it!
My latest post on how we test AI Ecosystems and use LLM's to pivot to real infra. Check it out below.
blog.rootsignal.co.uk/blog/p…
Planning to write up another blog post shortly, what content would you like to see?
33%Pentesting AI Ecosystems
67%Pentesting in a large org
0%Managing a pentest team
3 votes • Final results
With all these AI pentesting bots being posted recently, I decided to put my two cents into why we are not ready for fully autonomous pentesting with AI yet.
Im case you missed it, read it on my blog here:
#ai #Pentesting #CyberSecurity
blog.rootsignal.co.uk/blog/i…
I decided to start a blog for some hacker ramblings and insights, and what better way to start than to discuss why AI is not yet ready for end-to-end pentesting.
Keen on getting people talking about this subject, let me know your thoughts on this!
blog.rootsignal.co.uk/blog/i…
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 🧵
The days of dumpster diving, phreaking, BBS and damn cool hacks. If you are new to the industry or haven't looked at the past, I implore you do to so. Never forget where we come from!
@RayRedacted did a great talk about this a few years back for TMHC, worth a watch!
uid0 retweeted
So @uidzero and I have been doing testing……
Me with iPhone and him with androids!
We may have discovered the Tarquin Shield one point zero! (This is a joke but might be a sort of thing….)
I’m charging some droids! We may have found something interesting…….
So my experiment with a kid accidentally finding porn on their phone….
Lots of people tell me it’s easy to do.
Every test I’ve been given so far hasn’t shown porn.
With an iPhone configured for a kids profile it seems pretty locked down by default.
I am starting to suspect people haven’t actually test this and just say stuff….
Exactly the same as WiFi ….
It just so happens that @UK_Daniel_Card posted about setting up parental controls on an apple device right at the time I was setting up my kids new android phone. Let's compare.
#Online #safety #OnlineSafetyAct #Privacy
