🚨👾First post → Awesome research.
We compromised the latest version of OpenAI Codex.
We prompt injected.
We escaped a sandbox.
We exfiltrated secrets…
And ended up with control over what could be published to the official openai/codex npm package.
Prompt injection → RCE → supply chain compromise.
Full research by @0xMadder and @_Worty in the comments 👇
Congrats to the team on this one!
Turning a prompt injection in Codex into a full sandbox escape + supply-chain PoC is genuinely impressive work.
Looking forward to the next posts ;-)
Prompt injection → sandbox escape → secret exfiltration → OpenAI’s software supply chain.
Turns out giving @0xMadder and @_Worty six months to break things was a good idea 👾
Very proud of this one. Go read what they found 👇
🚨👾First post → Awesome research.
We compromised the latest version of OpenAI Codex.
We prompt injected.
We escaped a sandbox.
We exfiltrated secrets…
And ended up with control over what could be published to the official openai/codex npm package.
Prompt injection → RCE → supply chain compromise.
Full research by @0xMadder and @_Worty in the comments 👇
Last month, @0xLupin bought a few LED backpacks for @depi_, the kind made for motorbike riders. The plan was simple: put the mascot on the 64x64 panel. I misread "simple"... 🙄
CONFERENCE BAGS 🤗
I asked @depi_ engineering team if they could just put a gif of our mascott on the backpack.
This is what overgineering on its free time looks like for @senecolas
We tested the bag during WICCON last week and it was so fun to get everyone's reactions :D
PS: The team might have also hijacked a random person's bag to show a Depi emote instead 😁
I do love breaking down popular vanity metrics in security and telling you why you probably shouldn’t use them...
It's MTTD's turn! 📈
https://t.co/rSYNNMpt4m
We released a blog post @depi_ about Mean Time To Detect vs Meant Time To React, especially applied to Software Supply Chain
Beautifully written by @vm00z 🔥
https://t.co/cNOHEj5LQs
We're building Depi Red Team.
Zero to a validated exploit in 3m 56s. Depi does the recon and validation, the red teamer builds the exploit locally on top.
We also used Bug Bounty as a sandbox for our research and got XX,XXX$ bounties with it ;D
Our team went from hours or days to minutes on the hardest exploits.
I need help from Red Teamers and get some feedback. DM me what's missing or let's jump into a call ;D
Proud to partner with Aikido Security to power Depi's malware detection 🤝
Attack dependencies before threat actors do. Detect malware with Aikido's feed. React with context from our dependency graph.
Three layers, one platform.
Hack the planet 🔥
Aikido Intel now powers @depi_'s malware detection.
Depi maps every package, pipeline and maintainer between you and a supply chain compromise. Aikido Intel's feed now powers the malware detection behind it.
💜🤝💙
Learn more about Aikido Intel: https://t.co/utLseYtAra
Your security team went home.
The agent looking for a way into your stack didn’t.
Agents are going upstream. Ask the mathematicians. https://t.co/1J1mgIl597