MCP and Agent security with Luke Hinds
16 Mar 2026
The text explores AI agent security risks like prompt injection and open-source vulnerabilities, emphasizing the No-NO project's kernel-based sandboxing with a deny-by-default model, hardware enclaves, and Rust-driven efficiency, alongside layered defenses, restricted commands, and collaborative efforts to tackle evolving threats like social engineering and insecure coding practices.
Open episode







