permissions

Manage command execution approvals, tool access policies, and security controls for AI agents.

Updated Feb 5, 2026

Search Tags:#security #permissions #command execution #approval workflow #agent control #tool policy

Ready to run

npx skills add https://github.com/shreed27/DAIN --skill permissions-shreed27

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: permissions
Source: https://github.com/shreed27/DAIN/tree/main/CloddsBot-main/src/skills/bundled/permissions
Command: npx skills add https://github.com/shreed27/DAIN --skill permissions-shreed27

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides robust control over what commands and tools an AI agent can execute, preventing unauthorized actions and ensuring security.

Core Features & Use Cases

Command Approval: Manages a system for approving or rejecting commands before execution.
Tool Policies: Defines which tools an agent can access, with support for grouping tools.
Security Modes: Enforces different levels of command execution security (deny, allowlist, blocklist, full).
Use Case: Prevent an AI agent from accidentally deleting critical files by configuring an allowlist or blocklist for its commands, or require explicit approval for potentially dangerous operations.

Quick Start

Use the permissions skill to list all current allowlist entries for the default agent.

Frequently Asked Questions about permissions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I set up an allowlist to control AI agent command execution?▼

To control AI agent command execution, you can configure explicit allowlists and blocklists using the permissions skill. This enforces security by ensuring agents only run approved commands, preventing unauthorized actions and accidental damage.

Can I require manual approval before an AI agent runs dangerous commands?▼

Yes, you can require manual approval before an AI agent runs dangerous commands by enabling an approval workflow. The permissions skill manages this by intercepting command execution and holding potentially dangerous operations until explicit approval is granted.

What security modes are available for managing tool access policies?▼

Available security modes for managing tool access policies include deny, allowlist, blocklist, and full execution. These modes enforce different levels of command execution security to ensure deterministic task execution for AI agents.

How do tool policies prevent an AI agent from deleting critical files?▼

Tool policies prevent an AI agent from deleting critical files by defining specific tool access rules and grouping tools into profiles. Configuring a blocklist or explicit allowlist restricts access to destructive commands, safeguarding your system.

What is the best way to group tools for deterministic AI task execution?▼

The best way to group tools for deterministic AI task execution is by using tool profile expansion features. This allows you to define granular rule management and assign specific tool groupings to agents, ensuring strict security controls.

When should I use a blocklist instead of an allowlist for agent security controls?▼

Use a blocklist to explicitly forbid known dangerous commands while allowing all others, or an allowlist to restrict agent execution to only pre-approved safe commands. Choose allowlists for strict security and blocklists for flexible but controlled environments.