test

Verify allowed-tools coverage by exercising !-injection patterns across Bash, Python, and Read.

Updated Apr 19, 2026
One-click install
npx skills add https://github.com/jewzaam/jewzaam-reviews --skill test-jewzaam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test
Source: https://github.com/jewzaam/jewzaam-reviews/tree/main/skills/test
Command: npx skills add https://github.com/jewzaam/jewzaam-reviews --skill test-jewzaam

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The permission canary exercises every !-injection pattern used by real producer skills to verify allowed-tools coverage.

Core Features & Use Cases

  • Validates tool-access boundaries across Bash, Python, and Read patterns in skill execution.
  • Provides a safety check to ensure injection patterns are detectable and reportable during development and testing.
  • Use Case: A developer wants to confirm that all declared allowed-tools in a skill are honored by the runtime before enabling the skill in production.

Quick Start

Run the canary against a target skill directory to verify allowed-tools coverage and gather a report of outputs.

Frequently Asked Questions about test

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

FAQPage Schema
How do I verify allowed-tools coverage for skill injection patterns?

A permission canary validates that all declared allowed-tools in a skill are honored by the runtime by exercising every !-injection pattern across Bash, Python, and Read access before production deployment.

What is a permission canary in security testing?

A permission canary is a safety check that exercises every !-injection pattern used by real producer skills to verify allowed-tools coverage and ensure injection patterns are detectable and reportable during development.

How do I test tool-access boundaries across Bash, Python, and Read patterns?

You test tool-access boundaries by applying a permission canary during development, which exercises all !-injection patterns across Bash, Python, and Read access to validate allowed-tools coverage within plugins.

Can I use a permission canary to validate skill execution before production?

Yes, you can run the permission canary during development and testing to confirm that all declared allowed-tools in frontmatter are honored, ensuring safe, auditable test execution with constrained environment access.

Why does my allowed-tools declaration not match actual tool access during testing?

Your allowed-tools declaration may not match because untested !-injection patterns exist; running a permission canary exhaustively exercises every pattern to detect and report gaps in Bash, Python, and Read access.