Been a fan of chompie since her early Linux work, great interview! This is what real AI vuln research looks like. Full self bug hunting™ by end of year.
chainreactors/aiscan: pi-like agentic security scanner — single binary for AI-driven pentesting, from red team ops to bug bounty https://t.co/dzvZkSyA7n
I just wrote a new blog on bypassing CA policies in Entra ID that have a resource exclusion, and why you probably want to enable baseline enforcement if you have such policies. Enjoy!
https://t.co/a1rGl3wss8
Using a coding hardness? Hook NightBeacon up to it. Drop files, logs, whatever - have it automatically RE it, give full timeline of artifacts. Have it automatically spin up containers and detonate malware, snag all the IOCs, submit it to TI sources automatically. Runs through Suricata, Zeek, Hayabusa, CAPE, and many others including 10K+ yara rules.
Use velociraptor? Dump it in, automatically analyzes, reaches out via connectors to pull additional data if necessary, gives you full timelines.
Want to kick off a threat hunt ? Cool, ask NightBeacon to generate a hypothesis based threat hunt on the past week of activity, pushes through your connectors, brings results back and analysis.
Want to take action? "Contain these hosts". Done.
Just want to see how your org is doing? "How am I looking today?"
#BinaryDefense
UnCanny - Another new coercion primitive with LPE 0day - machine-account NTLM coercion from a non-admin user via Windows Store InstallService plugin resolution experiments https://t.co/Vw2LEhoZXZ
Defensive patch Tuesday semantic diff cli for Windows build snapshots for drivers, dlls, and more.
Microsoft, don't kill me. Thank you.
https://t.co/GEKZbTNyHO
I made this Windows security research toolkit for LPE, persistence, COM hijacking, and attack surface enumeration.
Leave a star and follow on GitHub so I can feed my 10 kids <3
https://t.co/esI60KXU2X
We're mostly an IDA shop at @CellebriteLabs, but I decided to play around with Ghidra. My main motivation was to experiment with agentic reverse engineering techniques. The result is an agent skill for Ghidra, which we are releasing publicly:
https://t.co/mPrNFR8mOq >>
If I have one recommendation to give, transform into deterministic workflows EVERYTHING you can to offload your agent.
This will:
- Save tones of tokens at runtime
- Make your workflow more deterministic and less reliant on the LLM to accomplish key steps
Tokens are cheap now and you should enjoy the party, but that will change. The more you build for the long term in a deterministic way, the more tokens you’ll save in the future, so you will spend less compare to your competitors, think about that.
So invest time in building your system, and thank me later.
Have you noticed that those deep-dive stories about complex Windows malware have pretty much vanished, especially in recent years? It feels like the era of "blockbuster" Windows malware has just gone silent, and this blog post tries to give some answers why.
https://t.co/sFsf3uPm5o
Powershell Scripts With 100% AV Bypass (PSSW100AVB) repository
https://t.co/fiLzzTgPjn
New undetectable PowerShell reverse shell added (May 4, 2026). 🔥 Essential for red teamers—use it in the next 2-3 weeks before it gets flagged!
#Powershell#RedTeam#ReverseShell
I thought Edge was always a sort of skinned Chromium? Didn't test it (yet) but do Chromium et al also have cleartext passwords in their dump?
Vibe coded Powershell version:
https://t.co/SuT3s580yI