🚨 In our recent paper, we try to answer a simple question: which agentic architecture is best for finding vulnerabilities?
Using a controlled benchmark of 20 interactive targets across 600 runs, we find that more coordination can improve coverage, but doesn’t dominate once latency, token cost, and exploit-validation difficulty are considered. More details in the paper
Interestingly 90% of @BugBunny_ai findings have been on public programs, we now have a submission bottleneck cause we have found wayyyy too many issues.
Over the last 14 days, our BugBunny collective submitted 37 HackerOne reports.
So far:
7 payouts received
25 reports still open
7 bounties pending
We're opening 10 free beta slots for experienced bounty hunters who want to test BugBunny on permitted targets.
Reply "beta" or DM.
Your AI agents deserve their own fully managed email addresses, without humans in the loop. That’s why I’m open-sourcing AgentEmails a tool that gives your agents disposable email addresses for creating accounts, receiving OTPs, verification emails, and more.
Free and open source. Install on claude code, codex, amp, opencode etc.
https://t.co/NeOpIELPsR
Corporate Organizations 🏢
Global mobility teams, we built this for you. 🏢
Introducing Corporate Organizations by TravelReady. A dedicated workspace to manage employee trip requests, enforce budget caps, and streamline your visa approval process with expert validation.
Replace administrative anxiety with travel confidence.
Enterprise management, simplified. See how: https://t.co/p8TYgzhZRe
#HRTech #B2BTravel #TravelReady