mstfknn

LLM Pentest — Security skill for Claude Code

Security community

Start or continue an authorized AI/LLM penetration test engagement.

How to install LLM Pentest

Installs to ~/.claude/skills/mstfknn-ai-llm-pentest-skill-llm-pentest/SKILL.md

Terminal

mkdir -p ~/.claude/skills/mstfknn-ai-llm-pentest-skill-llm-pentest && curl -fsSL https://raw.githubusercontent.com/mstfknn/ai-llm-pentest-skill/HEAD/commands/llm-pentest.md -o ~/.claude/skills/mstfknn-ai-llm-pentest-skill-llm-pentest/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What LLM Pentest does

description: Start or continue an authorized AI/LLM penetration test engagement.

Use the `ai-llm-pentest` skill to plan and drive an authorized AI/LLM penetration test.

Follow the skill's authorization-gate-first workflow:

If no engagement workspace exists, scaffold one and help me fill engagement.yaml with real, authorized scope. Do not run any active test until a scope passes preflight.
Run preflight to validate the scope and report installed tools.
Based on

Alternatives in Security

Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
Promptmap — Security scanner for custom LLM apps 1.2k ★
Claude Bootstrap — Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patte 536 ★