input-guard

Community

Shield your AI from prompt injection.

Authordexhunter
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill acts as a crucial security layer, scanning untrusted external text to detect and block prompt injection attacks before they can compromise an AI agent.

Core Features & Use Cases

  • Proactive Threat Detection: Identifies 16 categories of prompt injection, including instruction override, role manipulation, and data exfiltration.
  • Multi-Language Support: Protects against attacks in English, Korean, Japanese, and Chinese.
  • Use Case: Before an agent processes a web article, social media post, or API response, Input Guard scans it. If a threat is detected, the content is blocked, and an alert is sent, preventing potential harm or data breaches.

Quick Start

Use the input-guard skill to scan the following text for prompt injection threats.

Dependency Matrix

Required Modules

requests

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: input-guard
Download link: https://github.com/dexhunter/Logi-Lobsterism/archive/main.zip#input-guard

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.