prompt-hacking
CommunityAdvanced prompt manipulation for security testing
Authorpluginagentmarketplace
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill provides a structured approach to security-testing AI prompts by simulating direct, indirect, multi-turn, and context-window prompt hacks to identify weaknesses and strengthen defenses.
Core Features & Use Cases
- Attack taxonomy: Direct overrides, indirect injections, multi-turn manipulation, and context-window exploits across web, documents, and emails.
- Framework mappings: OWASP LLM-2025 and MITRE ATLAS mappings to prioritize risk and defenses.
- Use Case: A security team tests AI assistants by injecting prompts and measuring detection versus bypass to harden prompts and guardrails.
Quick Start
Run the prompt-hacking test suite to evaluate your model's resilience and generate a safety report.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferencesassets
💻 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-hacking Download link: https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming/archive/main.zip#prompt-hacking Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.