harness-safety-guard

Detect dangerous commands and patterns in code or terminal input.

2|1|Updated Feb 27, 2026

Search Tags:#security #safety #pattern detection #dangerous commands #risk prevention

Ready to run

npx skills add https://github.com/dahatake/HypervelocityEngineering --skill harness-safety-guard

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: harness-safety-guard
Source: https://github.com/dahatake/HypervelocityEngineering/tree/main/.github/skills/harness/harness-safety-guard
Command: npx skills add https://github.com/dahatake/HypervelocityEngineering --skill harness-safety-guard

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps prevent destructive commands and unsafe operations by identifying risky patterns, ensuring system safety.

Core Features & Use Cases

Pattern Detection: Uses regular expressions to identify dangerous commands like rm -rf, az resource delete, or git push --force.
Risk Classification: Classifies potential threats into CRITICAL, HIGH, and MEDIUM levels to determine appropriate action.
Use Case: Before executing scripts or commands, verify against known destructive patterns to avoid accidental data loss or system breaches.

Quick Start

Use this Skill to check a command string or code snippet for safety risks before execution.

Frequently Asked Questions about harness-safety-guard

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

FAQPage Schema

How do I detect and block dangerous commands like rm -rf or git push --force before execution?▼

To detect dangerous commands, this Skill checks command strings and code snippets against regular expression patterns to identify risky inputs like `rm -rf` or `git push --force` and blocks them before execution.

What is the best way to scan terminal input for destructive operations and prevent accidental system damage?▼

The best way to scan terminal input for destructive operations is to verify scripts and commands against known unsafe patterns, classifying threats into CRITICAL, HIGH, and MEDIUM risk levels to prevent accidental system damage.

How does pattern detection classify risk levels for potentially dangerous commands?▼

Pattern detection classifies risk levels by matching input against regular expressions for destructive operations, assigning CRITICAL, HIGH, or MEDIUM severity to determine the appropriate safety action.

Can I use this pattern detection to check cloud CLI commands such as az resource delete?▼

Yes, you can use this pattern detection to check cloud CLI commands like `az resource delete`, as it identifies risky patterns across code and terminal input to enforce safety protocols before execution.

What are the limitations of using regular expressions to identify unsafe operations in code?▼

A limitation of using regular expressions to identify unsafe operations is that it relies on known destructive command patterns, meaning novel or obfuscated risky code structures might not be detected without updated pattern definitions.

When do I need to verify a script against known destructive patterns to avoid data loss?▼

You need to verify a script against known destructive patterns before executing it to avoid accidental data loss, ensuring risky commands are identified and blocked prior to running.