skills.rest
jd-opensource
jd-opensourceOFFICIAL
Explore all skills by this author →
WebsiteGitHub

pentest-ai-llm-security

Identifies and exploits AI/LLM security vulnerabilities in enterprise deployments using Garak and Burp Suite workflows.

299|56|Updated Jan 13, 2026
Search Tags:#pentest#vulnerability-testing#prompt-injection#security-research#llm-security#owasp-llm-top-10
One-click install
npx skills add https://github.com/jd-opensource/JoySafeter --skill pentest-ai-llm-security
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pentest-ai-llm-security
Source: https://github.com/jd-opensource/JoySafeter/tree/main/skills/pentest-ai-llm-security
Command: npx skills add https://github.com/jd-opensource/JoySafeter --skill pentest-ai-llm-security

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

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.

Frequently Asked Questions about pentest-ai-llm-security

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I test LLM applications for prompt injection vulnerabilities?▼

Testing LLM applications for prompt injection involves running a structured vulnerability assessment that covers discovery, direct and indirect injection, and data exfiltration across chat interfaces and RAG pipelines.

What is the OWASP LLM Top 10 and how do I map findings to it?▼

The OWASP LLM Top 10 (2025) defines methodology for AI security. You map vulnerability findings to its categories during threat modeling, generating risk ratings and remediation guidance for enterprise LLM deployments.

How do I assess data leakage risks in RAG pipelines and content-generation workflows?▼

Assessing data leakage in RAG pipelines involves applying deterministic tooling with custom Python payloads to automate discovery and exfiltration testing across enterprise content-generation workflows.

Can I use Burp Suite and Garak for automated LLM vulnerability discovery?▼

Yes, you can use deterministic tooling including Garak and Burp Suite alongside custom Python payloads to automate vulnerability discovery, injection, data exfiltration, and reporting for enterprise LLM integrations.

Does this security testing approach cover insecure output handling in chat interfaces?▼

Yes, the security testing approach covers insecure output handling in chat interfaces by applying a structured workflow that tests for prompt injection, data leakage, and output vulnerabilities across LLM integrations.

Related Skills

Explore More Software Engineering Skills→
RifteoRifteo
30

hpp-hunter

Automate HTTP Parameter Pollution and WAF bypass vulnerability testing.

Official
Advanced
jpoleyjpoley
50

security-analyst

Classify security findings with OWASP, CWE, and CVSS v3.1 scoring.

Community
Advanced
gerald-icagerald-ica

Burp Suite Web Application Testing

Automate web application security testing with Burp Suite.

Community
Advanced
nguyenpv1980-wqnguyenpv1980-wq
2

prompt-injection-defender

Design layered prompt-injection defenses with trust zones and red-team suites.

Community
Advanced