AI Pentest

by SnailSploit

AI Pentest is an AI Engineering skill for Claude Code, published by SnailSploit in Claude-Red.

2.9K stars479 forkson SnailSploit/Claude-RedAdded 2026/08/17+1% in starsRepository updated 2026/05/08

View source on GitHub Download repo ZIP

claude-aiclaude-ptclaude-skillsredteamredteam-toolsskills

Install in seconds

Install AI Pentest

Copy AI Pentest into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/SnailSploit/Claude-Red/tree/main/Skills/ai/offensive-ai-security ~/.claude/skills/offensive-ai-security

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/SnailSploit/Claude-Red.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: Skills/ai/offensive-ai-security/SKILL.md in SnailSploit/Claude-Red
Installs to: ~/.claude/skills/offensive-ai-security
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What AI Pentest does

AI Pentest provides an offensive AI/LLM security checklist covering prompt injection, jailbreaking, model extraction, training data poisoning, adversarial inputs, and AI reconnaissance. Use it when assessing AI/ML systems, red-teaming LLMs, or researching AI attack vectors.

AI Pentest is cataloged under AI Engineering on DirSkills. AI Pentest comes from a repository tagged claude-ai, claude-pt, claude-skills, redteam and redteam-tools.

Documentation

README

Excerpt

SKILL: AI Pentest

Metadata

Skill Name: ai-security
Folder: offensive-ai-security
Source: https://github.com/SnailSploit/offensive-checklist/blob/main/ai.md

Description

AI/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.

Trigger Phrases

Use this skill when the conversation involves any of: AI security, LLM security, prompt injection, jailbreak, model extraction, training data poisoning, adversarial input, AI red team, ML security, RAG poisoning, AI attack

Instructions for Claude

This is the opening of the README. Read the full README on GitHub.

Frequently asked about AI Pentest

What else does SnailSploit publish alongside AI Pentest?
AI Pentest is one of 25 skills that DirSkills catalogs from SnailSploit/Claude-Red, the repository it ships in. Its siblings there include Advanced Red Team Ops, Basic Exploitation and Bug Identification. Each one is a separate skill with its own page in this directory, installs the same way AI Pentest does, and is maintained by SnailSploit in that same repository. The rest of the collection is listed on the SnailSploit/Claude-Red page.
How does AI Pentest compare to other AI Engineering skills?
AI Pentest ranks #697 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of AI Pentest against them. Open each page to compare what they document and how they install.