RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One line. Many voicesSeek and you shall find

www.anthropic.com faviconHow we contain Claude across products

kept by

Anthropic details how it contains AI agent blast radius across three products using sandboxes, VMs, and human-in-the-loop controls, while documenting missed risks like pre-trust code execution and user-mediated prompt injection.