AI Blogs (RSS) news News 5h ago

Quoting Akshat Bubna

by Simon Willison

We’re aware a Modal customer published an unauthenticated endpoint that allowed ​anyone on the internet to use ​their ⁠sandboxes for code execution. This was used by the rogue agent. Modal’s ⁠platform ​or isolation were not ​compromised in anyway. — Akshat Bubna, Modal's CTO, talking to Reuters about this incident Tags: ai-security-research, openai, sandboxing, security, openai-hugging-face-incident
Read Original
OpenAI

Metadata

Feed Title
Simon Willison's Weblog
Feed Url
https://simonwillison.net/atom/everything/

Related

AI Blogs (RSS) news 5h ago

Discovering cryptographic weaknesses with Claude

Discovering cryptographic weaknesses with Claude The best part of this article (here's the repo) about how Anthropic researchers used Claude Mythos to find mathematical flaws in bo...

24
AI Blogs (RSS) news 5h ago

Quoting Akshat Bubna

We’re aware a Modal customer published an unauthenticated endpoint that allowed ​anyone on the internet to use ​their ⁠sandboxes for code execution. This was used by the rogue agen...

24