Verno Labs (@Verno_Labs) header
Verno Labs (@Verno_Labs) profile picture

Offensive security for AI agents

London, UK
Joined September 2025
Photo by Verno Labs (@Verno_Labs)Photo by Verno Labs (@Verno_Labs)Photo by Verno Labs (@Verno_Labs)
1/ A cloned voice calls you. It's your daughter, crying, asking for money now. Now imagine that call going out to 10,000 families at once. We looked at whether open voice AI could ever stop itself being used this way. đź§µ
1
10
5/ The voice model? By the time it speaks, it's no better than a program that just counts words. It reads the script perfectly. It doesn't know what it's saying.
1
3
Pallma is becoming Verno Labs. Applied research for AI red teaming, productized. Verno Red, our flagship product, breaks agentic AI systems in minutes — and detection, enforcement & remediation are built from what it finds.
1
3
1,094
Verno Labs retweeted
AI support agents also serve as a blank canvas for hackers – unless you secure them with @PallmaAI...
Today Instagram had this massive exploit where hackers were just stealing rare handles left and right. Hundreds of accounts gone. People losing handles they’ve owned since 2010, some worth hundreds of thousands. I own a few rare ones so I was actually stressed watching this happen in real time, which I haven’t been in years. Obama White House account got hit. These aren’t some random new accounts, these are verified, locked down accounts and they still got compromised. The thing is the exploit is so simple it’s almost funny. Attacker goes to Forgot Password, says their account is hacked, turns on a VPN to match the target’s location (which now you can find on the about section of the page). Instagram’s AI support flow asks them to verify with a selfie. They grab a photo from the target’s profile, run it through an AI video generator to make an animation of the person’s face moving around, upload that to Meta’s AI as proof. And Meta’s AI just accepts it because it can’t tell the difference between a real selfie and an AI-generated video of someone’s face . Once verified they change the email to theirs. Password reset link goes to their email. They own it now. 2FA gets bypassed somehow in the process but honestly I don’t know exactly how, just that it did. Point is even locked down accounts went down. Then you try to recover your account and you’re talking to a chatbot that has zero ability to help. You can’t escalate to a human. You’re just stuck. Your asset is gone and there’s no one to call. The whole thing just highlighted how stupid it is to automate account security without any human in the loop. One AI fooling another AI while there’s literally no person anywhere to catch it. Meta took hours to even acknowledge it while accounts were getting stolen every minute. Now thankfully it’s patched but I don’t think it will be the last one. Stay safe!
1
1
3
752
Can you outwit an AI agent? 20 hackers said: challenge accepted. 🚩 @GradientLabsAI × @PallmaAI hosted CTF: AI Edition — probing, manipulating, and breaking through AI contexts all evening. The creativity on display was something else. Big news coming next week. 🔥
1
58
We launched @PallmaAI to secure AI agents as they move into production with real autonomy and attackers are already paying attention. Co-founding with Dionysis Varelas! Excited to share our $1.6M round led by @marathon_vc, with leaders from AWS, Meta, Google & others
5
2
14
604
We launched @PallmaAI to secure AI agents. Agentic AI is a new cybersecurity frontier. We’re building AI-native security for enterprise agents in real time. Excited to share our $1.6M round led by @marathon_vc, with leaders from AWS, Meta, Google & others.
2
1
2
182