Anthropic publishes a Zero Trust framework for enterprise AI agents

"Zero Trust for AI Agents" adapts zero-trust security principles — never trust, always verify; assume breach; least privilege — to autonomous agents, covering identity, access control, memory-poisoning defense, and behavioral monitoring across a three-tier (Foundation/Advanced/Optimized) maturity model aimed at regulated industries.

What it means A useful audit checklist even outside Anthropic's own stack — the seven control domains it names are a reasonable starting list for anyone standing up agents with real write access.