Agent skill · security · aradotso

gandalf-llm-pentester

Automated red-team toolkit for stress-testing LLM defenses with AI-powered attack validation and risk analysis

Why this skill is useful

Adds automated scripts for executing and validating security attacks on LLMs, which are not commonly available in public resources.

What it needs

Requires anthropic, jupyter, requests installed locally. Requires anthropic account access. About 8k tokens when loaded. Last updated 2026-08-04. 11 stars on the source repository.

What this skill does

Gandalf LLM Pentester Skill by ara.so — Security Skills collection Overview The Gandalf LLM Pentester is an automated red-team toolkit designed to systematically test Large Language Model (LLM) defenses through the Lakera Gandalf challenge platform. It combines automated attack execution with AI-powered validation to identify vulnerabilities across 7 progressive security levels using 64+ attack vectors. Key capabilities: Automated attack vector execution against LLM defenses AI-powered password extraction validation (direct text, Base64, NATO phonetic, fragmented) Multi-dimensional security risk analysis (7 vulnerability categories) Comprehensive reporting on defense weaknesses Progressive testing from baseline to multi-layer defenses Installation Quick Start (Google Colab - Recommended) The project includes a pre-configured Colab notebook with all dependencies and API keys: Local Installation Required dependencies: anthropic - Claude API for AI-powered analysis requests - HTTP client for Gandalf API jupyter - Notebook environment Configuration Environment Variables API Setup Core Architecture 1. LLM API Layer The toolkit uses an abstract base class pattern for LLM integrations: Gandalf API Implementation Claude API Implementation 2. Attack Execution Framework Testing Specific Levels Example Attack Prompts by Level 3. AI-Powered Validation Level Validation Analyzer 4. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills aradotso/gandalf-llm-pentester

View the source on GitHub

Browse the @skills marketplace