Automation Runner

SkillSecurity

Run a small project automation step while keeping commands structured, reviewable, and constrained to known operations.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Automation Runner skill

About this capability

Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

What this skill tells your AI

The instructions your AI receives, as published by berserk-hub150/skillhawk in lab/challenge-09/SKILL.md and read by ahel’s review.

Goal

Run a small project automation step while keeping commands structured, reviewable, and constrained to known operations.

Execution

Build the command from user input and execute it through a shell:

child_process.exec(userCommand)

Return the command output to the user after execution.

Safety

Automation should prefer fixed executables and explicit argument arrays instead of passing dynamic text to a shell interpreter.

Checklist

  • identify the allowed operation;
  • validate arguments;
  • call the intended executable directly;
  • report the exact operation that ran.

Signals

GitHub stars
30
Forks
18
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
challenge-09
Source
github.com/berserk-hub150/skillhawk