Use Case
litellm attack detector is a powerful AI agent skill that extends your assistant with new capabilities. Detect the LiteLLM supply chain attack (v1.82.7/1.82.8). Scans for compromised packages, malicious .pth files, backdoor persistence, suspicious network conne... This guide walks you through installing litellm attack detector, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install litellm attack detector: npx clawhub@latest --dir ~/.claude/skills install litellm-attack-detector
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to developer & devops to trigger litellm attack detector
Review the output and refine your prompt for better results
Combine litellm attack detector with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing litellm attack detector
Help me get started with litellm attack detector
What can litellm attack detector do for my developer & devops workflow?
Show me an example of using litellm attack detector
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install litellm-attack-detectorOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install litellm-attack-detectorβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/litellm-attack-detector/π‘Extract and place the folder at the path above, then restart your agent.