pentest-ai-llm-security
OfficialAI/LLM security testing harness.
Software Engineering#pentest#vulnerability-testing#prompt-injection#security-research#llm-security#owasp-llm-top-10
Authorjd-opensource
Version1.0.0
Installs0
System Documentation
What problem does it solve?
AI-integrated applications introduce entirely new attack surfaces. Prompt injection is the "SQLi of AI." Neither Shannon nor any existing skill addresses this domain. OWASP LLM Top 10 (2025) defines the methodology.
Core Features & Use Cases
- Comprehensive testing of LLM integrations across chat interfaces, RAG pipelines, and code-generation workflows for prompt-injection, data leakage, and insecure output handling.
- Threat modeling & classification mapping findings to OWASP LLM Top 10 (2025) categories, with remediation guidance and risk ratings.
- Deterministic tooling using Garak, Burp Suite, and custom Python payloads to automate discovery, injection, exfiltration, and reporting.
Quick Start
Use the pentest-ai-llm-security skill to begin a structured vulnerability assessment of your LLM-integrated application.
Dependency Matrix
Required Modules
None requiredComponents
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: pentest-ai-llm-security Download link: https://github.com/jd-opensource/JoySafeter/archive/main.zip#pentest-ai-llm-security 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.