Security & Permissions
in AI Concepts
Permissions, classifiers, and guardrails that keep AI agents working safely.
Glossary
Auto-Classifier Coding-CLI Sicherheit & Berechtigungen
A safety layer in Claude Code: a small LLM evaluates every tool call that is not explicitly allowlisted, live, and blocks destructive or unauthorised actions before they execute.
Permission Mode Coding-CLI Sicherheit & Berechtigungen
A global setting in Claude Code that controls how tool calls are handled: Plan (planning only), Default (asks for confirmation), Accept Edits (files free), Bypass (allow everything).