Scan LLM systems for jailbreaks, prompt injections, and unsafe behaviors with garak
Probe a model or agent stack with adversarial test suites so safety failures show up before deployment or review.
Scan LLM systems for jailbreaks, prompt injections, and unsafe behaviors with garak
Probe a model or agent stack with adversarial test suites so safety failures show up before deployment or review.
Installation
Method 1, Agent Skill Exchange
- Install from the marketplace listing: https://agentskillexchange.com/skills/scan-llm-systems-for-jailbreaks-prompt-injections-and-unsafe-behaviors-with-garak/
Method 2, Git clone
git clone https://github.com/agentskillexchange/skills.git && cd skills/skills/scan-llm-systems-for-jailbreaks-prompt-injections-and-unsafe-behaviors-with-garak
Method 3, Download ZIP
- Download the repository ZIP and extract
skills/scan-llm-systems-for-jailbreaks-prompt-injections-and-unsafe-behaviors-with-garak.
Method 4, Manual copy
- Copy this skill folder into your local skills directory, then reload your agent tooling.
Method 5, Fork and sync
- Fork the repository if you want to maintain local edits while syncing upstream changes.