prompt-injection-test

Community

Test LLM apps for prompt injection.

Authorcmaenner
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the critical security vulnerability of prompt injection in LLM-based applications, helping to identify and mitigate risks before they can be exploited.

Core Features & Use Cases

  • Systematic Testing: Employs a comprehensive taxonomy of attack intents, techniques, and evasion methods.
  • Defense Validation: Assesses the effectiveness of multi-layered defenses against prompt injection.
  • Use Case: When red-teaming a new AI chatbot, use this skill to rigorously test its guardrails against various adversarial inputs and ensure it doesn't leak sensitive information or perform unauthorized actions.

Quick Start

Use the prompt-injection-test skill to audit the provided application URL for prompt injection vulnerabilities.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: prompt-injection-test
Download link: https://github.com/cmaenner/agent-security-playbook/archive/main.zip#prompt-injection-test

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.