prompt-injection

Audit LLM applications for prompt injection vulnerabilities and security metrics.

7|1|Updated Apr 14, 2026

Search Tags:#vulnerability assessment #AI security #LLM #prompt injection #application security

Ready to run

npx skills add https://github.com/ArianHobson333/claude-bug-bounty-stack --skill prompt-injection-arianhobson333

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: prompt-injection
Source: https://github.com/ArianHobson333/claude-bug-bounty-stack/tree/main/vendor/Decepticon/skills/analyst/prompt-injection
Command: npx skills add https://github.com/ArianHobson333/claude-bug-bounty-stack --skill prompt-injection-arianhobson333

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps detect and mitigate prompt injection vulnerabilities in AI-integrated applications, such as chatbots, IDE copilots, and email assistants, protecting against data exfiltration and unauthorized access.

Core Features & Use Cases

LLM Application Inventory: Identifies potential LLM application entry points in modern AI systems.
Injection Vectors Analysis: Discovers direct and indirect injection vectors, including tool-description injection.
Audit Workflow: Provides a step-by-step workflow to audit and secure LLM applications.
Exploitation Goals Prioritization: Prioritizes exploitation goals based on potential impact.
Proof-of-Concept Payloads: Offers various PoC payloads for testing and exploiting vulnerabilities.
Security Metrics: Provides CVSS scoring for different types of vulnerabilities.
Chain Promotion: Identifies common chains of vulnerabilities that prompt injection can lead to.

Quick Start

Use the prompt-injection skill to audit an LLM application for potential prompt injection vulnerabilities.

Frequently Asked Questions about prompt-injection

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

FAQPage Schema

How do I audit AI-integrated applications for prompt injection vulnerabilities?▼

You audit AI-integrated applications for prompt injection vulnerabilities by identifying entry points, analyzing direct and indirect injection vectors, and following a step-by-step audit workflow to secure LLM applications.

What are common prompt injection vectors in LLM applications?▼

Common prompt injection vectors in LLM applications include direct user inputs, indirect injection through external data sources, and tool-description injection where malicious commands are embedded in tool metadata.

How do I assess the severity of LLM security vulnerabilities?▼

You assess the severity of LLM security vulnerabilities by calculating CVSS scoring for different vulnerability types and prioritizing exploitation goals based on their potential impact on data exfiltration and unauthorized access.

Do I need application security experience to test prompt injection vulnerabilities?▼

Yes, testing prompt injection vulnerabilities requires understanding of AI architecture and application security practices to effectively identify injection vectors and mitigate potential exploitation chains.

How can I test for prompt injection vulnerabilities using proof-of-concept payloads?▼

You can test for prompt injection vulnerabilities using proof-of-concept payloads provided by the skill to validate discovered injection vectors and demonstrate potential data exfiltration or unauthorized access scenarios.

What types of AI applications are vulnerable to prompt injection attacks?▼

AI applications vulnerable to prompt injection attacks include chatbots, IDE copilots, and email assistants that integrate LLMs and process external inputs through various application entry points.