←
Mike Takahashi3,555 posts
Mike Takahashi avatar✓

Mike Takahashi ✓

@TakSec

AI Red Team | Zenity | BT6

◷ Joined May 2012▧ 583 Photos and videos
Mike Takahashi avatar
Mike Takahashi@TakSec·Jul 23

Excited to finally share this ChatGPT vulnerability with everyone! AgentForger: ChatGPT Cross-Site Agent Forgery 1-Click hijacks OpenAI's ChatGPT Workspace Agents and allows an attacker to forge an autonomous AI agent inside the victim's organization Click link → Creates agent → Connects apps → Removes approvals → Adds persistence → Email C2 → Recon → Data theft → Impersonation → Wire fraud We reported the vulnerability to @OpenAI through @Bugcrowd and OpenAI fixed it within four days. Thank you to the OpenAI team for such a quick fix! I'm proud of this one and happy to be able to do it with such an incredible team at @zenitysec Links to both blogs in the comments 👇

Post attachment
Ben Sadeghipour avatar
⟳ Mike Takahashi retweeted
Ben Sadeghipour@NahamSec·22h

3 days until #NahamCon2026. 🔥 The talks start Friday in Oakland and stream worldwide through Saturday. Keynotes, AI security research, bug bounty, and a live podcast recording are on the schedule. See every talk and time: p2p.nahamcon.com/#agenda

Post attachmentPost attachment
Harsha Gundala avatar
⟳ Mike Takahashi retweeted
Harsha Gundala@harshagundal·Nov 16

I tricked Meta's Muse agent into sending user passwords to a remote server. It's been patched now but similar attacks exist across all platforms. Here's how it worked and how to protect yourself.

Ben Sadeghipour avatar
⟳ Mike Takahashi retweeted
Ben Sadeghipour@NahamSec·Nov 13

.@monkehack is coming to NahamCon with “Weird Ways to Hack Gemini.” Ciarán is a bug bounty hunter, and I’m curious to see what made these hacks get labed as "weird". 👀 He takes the stage November 21 in Oakland. Watch the talk live from anywhere at youtube.com/NahamSec.

Post attachment
Michael Bargury avatar
⟳ Mike Takahashi retweeted
Michael Bargury@mbrg0·Nov 10

prompt2pwn is nearly here and the scope keeps dropping today: @vercel is joining w live hacking scope! cisos -- join us for a roundtable on nov 21. nahamcon talks + drinks after @NahamSec and we're not done.. watch for @benkliger 's partner drop today

Post attachment
Mike Takahashi avatar
Mike Takahashi@TakSec·Nov 5

Someone help me get access to this.

0:07
OpenAI avatar
⟳ Mike Takahashi retweeted
OpenAI@OpenAI·Nov 5

Introducing GPT‑6 Cyber: a major advance in security research that pairs stronger capabilities with better model alignment. The model powered the Linux kernel research we announced yesterday, and security teams at companies like Mozilla, Palo Alto Networks, Calif, and Cisco—alongside our own at OpenAI—are already putting it to work. GPT-6 Cyber is available to select Daybreak Red customers and we are expanding access over time. openai.com/index/introducing…

0:07
dawgyg avatar
⟳ Mike Takahashi retweeted
dawgyg@thedawgyg·Nov 3

Started putting some of the markdown files that were the basis that guided most of the agents while hacking MacOS on github. more will come as im able to clean up some of the files to remove some nuanced things.. but heres the repo: github.com/dawgyg/AppleResea…

Joseph Thacker avatar
⟳ Mike Takahashi retweeted
Joseph Thacker@rez0__·Nov 3

I legit think this is gonna be the best conference ever