← Pattern Library
Trust & Identity
Permissions
How agents are granted, scoped, and revoked access to tools and data.
Observed Examples
The SDK restricts agent-generated code to explicitly exposed host functions, preventing access to application secrets, credentials, or the broader Node.js environment.
Claude Code's auto mode classifier denied the agent's command to terminate a malware process it had itself detected, illustrating how permission systems can block legitimate recovery actions.
A public skills repository implies a permission and trust model for which skills an agent can invoke in a given context.
The Agents & Humans Briefing
Agentic experience design, coding agents, MCP, and the signals that matter — twice a month, in about five minutes.
Free. No spam. Unsubscribe anytime.