Pinned Tweet
Happy to share that my colleague @vudq16 and I will be speaking at PHDays in Moscow 🇷🇺 next week, May 24th. I’ll share a story from one of our red team projects, with techniques to maximize stealth during the operation.
Hope to make new connections there:D
phdays.com/en/forum/program/…
@msftsecresponse please check this case, this is not Spoofing!!!
guys you do know you can just disable thinking, and instead give it a "deep_think" tool, and it will call it with internal CoT reasoning format right?
gl fixing that
Q5Ca retweeted
We can finally talk about it:
We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company.
We verified that our reasoning token count matches billed API thinking tokens 1:1 for most of the prompts we queried.
Q5Ca retweeted
Seems that wp2shell PoCs are now floating around the internet, so we've published our blog post including our research methodology for finding the bug as well as a deep dive into the chain itself - slcyber.io/research-center/e…
Q5Ca retweeted
Booyah it's been confirmed! 🎉 splitline (@_splitline_) of DEVCORE Research Team chained 2 bugs to exploit Microsoft SharePoint, earning $100,000 and 10 Master of Pwn points. Massive aura farming this year at #P2OBerlin. Full win! #Pwn2Own
Q5Ca retweeted
And this one is human insight w/ LLM-assisted research. Took about one week to finish everything. The AI really rescued me from a lot of tedious work
— excluding the part where it changed the Domain Admin password, locked me out, and claimed it got RCE 🤦
Aaaand it's official! Orange Tsai (@orange_8361) of DEVCORE Research Team chained 3 bugs to achieve Remote Code Execution as SYSTEM on Microsoft Exchange, earning a whooping $200,000 and 20 Master of Pwn points. Full win! #Pwn2Own #P2OBerlin
Q5Ca retweeted
Locked in! Le Duc Anh Vu (@vulda17) of Viettel Cyber Security (@vcslab) exploited Cursor, earning $30,000 and 3 Master of Pwn points. Full win! #Pwn2Own #P2OBerlin
Q5Ca retweeted
Aaaand it's official! Orange Tsai (@orange_8361) of DEVCORE Research Team chained 3 bugs to achieve Remote Code Execution as SYSTEM on Microsoft Exchange, earning a whooping $200,000 and 20 Master of Pwn points. Full win! #Pwn2Own #P2OBerlin
Q5Ca retweeted
There it is! Orange Tsai (@orange_8361) of DEVCORE Research Team was able to exploit Microsoft Exchange! If confirmed, they win a whooping $200,000 and 20 Master of Pwn points. Off to the disclosure room to explain how they did it and seal the deal. #Pwn2Own #P2OBerlin
Q5Ca retweeted
Boom! @rewhiles of Viettel Cyber Security was able to exploit Anthropic Claude Code! If confirmed, they win $40,000 and 4 Master of Pwn points. They're off to the disclosure room to explain how they did it. #Pwn2Own #P2OBerlin
Q5Ca retweeted
That's my chain — a full chain w/ logic bugs only! No memory corruption, no AI, and of course no collisions at all 😉
Confirmed! Orange Tsai (@orange_8361) of DEVCORE Research Team (@d3vc0r3) chained 4 logic bugs to achieve a sandbox escape on Microsoft Edge, earning $175,000 and 17.5 Master of Pwn points. Full win! #Pwn2Own #P2OBerlin
Ước 🥹
Blog for ToolShell
Disclaimer: The content of this blog is provided for educational and informational purposes only.
blog.viettelcybersecurity.co…
#SharePoint #ToolShell
Slide: 1drv.ms/p/c/362121a38b7470ea…
Recording: youtube.com/watch?v=xBnMrNCu…
Just a quick reminder: Copilot on microsoft365.com (m365.cloud.microsoft/chat) is not on scope for bounty 🥲
duongq5ca.substack.com/p/ano…
Congrats @_l0gg! You did the thing I thought was impossible. Hard work pays off 💪
Confirmed!! Dinh Ho Anh Khoa (@_l0gg) of Viettel Cyber Security combined an auth bypass and an insecure deserialization bug to exploit #Microsoft SharePoint. He earns $100,000 and 10 Master of Pwn points. #Pwn2Own #P2OBerlin
Q5Ca retweeted
* People ask LLMs to write code
* LLMs recommend imports that don't actually exist
* Attackers work out what these imports' names are, and create & upload them with malicious payloads
* People using LLM-written code then auto-add malware themselves
vulcan.io/blog/ai-hallucinat…




























