offensive-ai-security

1# SKILL: AI Pentest
2 
3## Metadata
4- **Skill Name**: ai-security
5- **Folder**: offensive-ai-security
6- **Source**: https://github.com/SnailSploit/offensive-checklist/blob/main/ai.md
7 
8## Description
9AI/LLM security offensive checklist: prompt injection, jailbreaking, model extraction, training data poisoning, adversarial inputs, LLM-assisted attack automation, and AI system reconnaissance. Use when assessing AI/ML systems, red-teaming LLMs, or researching AI attack vectors.
10 
11## Trigger Phrases
12Use this skill when the conversation involves any of:
13`AI security, LLM security, prompt injection, jailbreak, model extraction, training data poisoning, adversarial input, AI red team, ML security, RAG poisoning, AI attack`
14 
15## Instructions for Claude
16 
17When this skill is active:
181. Load and apply the full methodology below as your operational checklist
192. Follow steps in order unless the user specifies otherwise
203. For each technique, consider applicability to the current target/context
214. Track which checklist items have been completed
225. Suggest next steps based on findings
23 
24---
25 
26## Full Methodology
27 
28# AI Pentest
29 
30## Shortcut
31 
32- Understand the AI system, its components (LLM, APIs, data sources, plugins), and functionalities. Identify critical assets and potential business impacts.
33- Collect details about the model, underlying technologies, APIs, and data flow.
34- Vulnerability Assessment:
35  - Use tools like `garak`, `LLMFuzzer` to identify common vulnerabilities.
36…