We exploited a lack of isolation mechanisms in multiple agentic browsers to perform attacks ranging from the dissemination of false information to cross-site data leaks. These attacks resurface decades-old patterns of vulnerabilities that the web security community spent years building effective defenses against.

Local LLMs prioritize privacy over security. Our research reveals a 95% backdoor injection success rate. If you’re running a local LLM for privacy and security, you need to read this

This weblog features the work of developer Simon Willison, primarily focusing on the latest developments in AI, large language models (LLMs), prompt injection vulnerabilities, coding agents, and related software and security topics.

It’s a good idea to use AI to review the security of your code, although you may get surprising results!

A really good presentation on the security vulnerabilities of today

Web review of Ervin