Tag: security

Simon Willison on the lethal trifecta and MCP security

A look at Simon Willison's latest talk on AI security, focusing on his 'lethal trifecta' concept and the risks of the Model Context Protocol (MCP).

Security risks in LLM agents: Simon Willison’s insights

A summary of Simon Willison’s recent posts on security risks in LLM agents, including the lethal trifecta, design patterns, and real-world vulnerabilities.

More tags: