prompt-injection-tester

Community

Test system prompts against adversarial probes.

Authorthejordanleopold
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the evaluation of system prompt robustness by running 225+ adversarial probes and quantifying resistance with a trust score, enabling red-teaming and reproducible security assessments.

Core Features & Use Cases

  • Automated prompt-robustness testing against extraction and injection probes to reveal weaknesses before deployment.
  • Manual probe battery that lets researchers reproduce reported attacks and validate defenses.
  • Integrates with or without AgentSeal for automated scoring, and provides remediation guidance based on results.

Quick Start

Run the included scripts/run-probes.sh with your prompt file and target model to start automated testing.

Dependency Matrix

Required Modules

None required

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: prompt-injection-tester
Download link: https://github.com/thejordanleopold/claude-code-skills-distilled/archive/main.zip#prompt-injection-tester

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 471,000+ vetted skills library on demand.