eric-burel
Joined 4 years ago
Karma
385
Submissions
187
Member since
Feb 16
Recent submissions
Comment · 6 months ago
Infrastructure provisioning is a key ingredient of agentic AI viruses: https://www.ericburel.tech/blog/ai-virus-agent
This may be the first steps of the worst wave of spamming campaign ever seen on the Internet. We'll need to reinvent how we connect and communicate via computers.
Comment · 8 months ago
They love their dictator until it backfires, that's a quite old story.
Comment · 8 months ago
I've been working on making the "lethal trifecta" concept more popular in France. We should dedicate a statue to Simon Wilinson: this security vulnerability is kinda obvious if you know a bit about AI agents but actually naming it is incredibly helpful for spreading knowledge.
Reading the sentence "// indirect prompt injection via email" makes me so happy here, people may finally get it for good.
Comment · 9 months ago
Can it be used to sandbox an AI agent, like replacing eg Cursor or Openclaw sandboxing system?
Comment · 9 months ago
The thing is running it onto your machine is kinda the point. These agents are meant to operate at the same level - and perhaps replace - your mail agent and file navigator. So if we sandbox too much we make it useless.
The compromise being having separate folders for AI, a bit like having a Dropbox folder on your machine with some subfolders being personal, shared, readonly etc.
Running terminal commands is usually just a bad idea though in this case, you'd want to disable that and instead fine tune a very well configured MCP server that runs the commands with a minimal blast radius.
Comment · 9 months ago
Before using make sure you read this entirely and understand it:
https://docs.openclaw.ai/gateway/security
Most important sentence: "Note: sandboxing is opt-in. If sandbox mode is off"
Don't do that, turn sandbox on immediately.
Otherwise you are just installing an LLM controlled RCE.
There are still improvements to be made to the security aspects yet BIG KUDOS for working so hard on it at this stage and documenting it extensively!! I've explored Cursor security docs (with a big s cause it's so scattered) and it was nothing as good.
Comment · 10 months ago
Related: https://news.ycombinator.com/item?id=46223311
Switching to paid version was already problematic as it uses GCP account system which doesn't have a spending limit, and API keys do not have an expiration date. So the free offer was great for freelancers and SMEs and yet the paid version was the worst possible scenario you can imagine for same freelancers and SMEs. OpenRouter + free models and the increased rate limit you get after buying 10 credits (10€) is my current favourite choice for learning/teaching.
Comment · 10 months ago
Microsoft is using the deep penetration of SharePoint in companies to sell Copilot license. At least in France it's well and alive and I see much more Copilot licenses than actual OpenAI uses.
Comment · 11 months ago
Yeah I mean you can replace sandboxing buy other safe alternatives but the idea is the same, the generated code has to be considered as 100% untrusted. Supply chain attacks are especially nasty.
Comment · 11 months ago
Talking about the debt of a system prompt feels really weird. A system prompt tied to an LLM is the equivalent of crafting a new model in the pre-LLM era. You measure their success using various quality metrics. And you improve the system prompt progressively to raise these metrics. So it feels like bandaid but that's actually how it's supposed to work and totally equivalent to "fixing" a machine learning model by improving the dataset.
Member of Devographics (State of JS survey) https://www.devographics.com/
https://bsky.app/profile/ericburel.tech