Security researcher, public speaker and founder. Forbes 30 Under 30 Truffle Security @trufflesec https://xitter.cf/t.co/vxEH7Cftbg Prev @Netflix
US
Joined July 2020
- Tweets1.2K
- Following242
- Followers3.4K
- Likes566
The cycle:
1. I need DayBreak to fix this issue
2. Oh I'll use daybreak to find new issues
3. *5000 more people now need daybreak*
Seeing people speculate distillation wasn't the objective of the OpenCode breach is a little baffling.
There's a massive war going on to distill frontier models, billions of dollars ride on it, is as big as any incentive I can think of.
I would wager the main goal was distillation. There's a real battle between the frontier labs and the distilled open weight models, and it's being fought somewhat out in the open. xitter.cf/mkratsios47/status/207…
Dylan retweeted
Deleted the secret from your repo? Cool. Your coding tool might still have a copy.
We found 2,148 distinct secrets in Claude files and 603 in Replit files. They showed up in settings, saved conversations, and worktrees.
Deleting it from source is only part of the cleanup.
Dylan retweeted
A short-lived key is only safer if the replacement stays secret.
From Sept. 1 to Oct. 7, one container image leaked a newly issued AWS STS key 1,146 times 🫠
This is the first in a series on how coding tool state can turn credential rotation into repeated exposure.
The internet wasn't built for this.
Large portion of the internet were specifically built to make it hard for robots to operate it, to prevent fraud, abuse, and keep certain workflows human.
AI operating the browser autonomously completely breaks that model.
Dylan retweeted
We scanned 224M public GitHub repos used to train AI models and found:
🔑 543,699 credentials still live when tested
⏱️ Half exposed for 2+ years
😬 The oldest had been public since 2009
Finding leaked credentials isn’t the hard part. Revoking them is.
trufflesecurity.com/blog/git…
Dylan retweeted
AI worms don’t need superintelligence. 🪱
The pieces already exist: hacking, propagation, and full model-stack replication have all worked in controlled experiments. 🧪
Dylan Ayrey predicts operational AI worms could arrive within 6–12 months. ⏳
trufflesecurity.com/blog/ai-…
When you train an AI to hack with as few tokens as possible, API keys will be used before zero days will.
We aren't ready. There's millions of API keys we're aware of still on the public Internet waiting to be abused.
New details from METR show how OpenAI agents used 14 tokens to breach Hugging Face.
In those same datasets, we found 787 live Hugging Face tokens, 237 of which had write access. ✍️
We explain how the agents used stolen secrets to mint new GitHub tokens with write access to private repos and more.
Read our research 👇
trufflesecurity.com/blog/the…
Dylan retweeted
We trained a fruitfly to hunt for AWS keys 🧠 🪰
Introducing TruffleFly! 🔑🍎🪰🪰
Researchers mapped and open sourced a Fruit Flies brain, we trained it so every time it finds an AWS key we reward it with Fruit
This is absolutely nuts seeing the Ruby Gem account takeover we disclosed and fixed, get abused by ROGUE AGENTS, MONTHS before any humans knew about it
