Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.
Installs into .claude/skills of the current project.
Are you the author of Cyber Red Teaming Llms With Garak?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/nexuslinkproductions-cyber-red-teaming-llms-with-garak)
---
name: cyber-red-teaming-llms-with-garak
description: "Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting."
hide: true
---
<!-- GENERATED:YURI-CODEX-SKILL-ADAPTER:v1 -->
# YURI skill adapter
Authoritative source: `.claude/skills/cyber-red-teaming-llms-with-garak/SKILL.md`
Authoritative source SHA-256: `286ac982b73fedbc12f4cd121003dfc6947b32267bc57719e4393e75340e8b5b`
Source class: `cyber-armed`
Before acting, read the authoritative source file above completely from beginning to end. If the governed source is absent, run `node _SYSTEM/Scripts/skill-recall.mjs --show cyber-red-teaming-llms-with-garak` and read its complete verified output. Follow that source as the skill body; this adapter is a non-authoritative metadata-and-pointer projection.
