🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
BytesAgain β€Ί Skills β€Ί Know your AI
πŸ¦€ ClawHub

Know your AI

by @juhengwu

Command-line tool for red-team AI security testing, running evaluations, detecting vulnerabilities, and reviewing detailed results via API integration.

Versionv1.0.2
Downloads195
#finance#legal
TERMINAL
clawhub install know-your-ai

πŸ“– About This Skill

---
name: know-your-ai
description: AI security testing & evaluation CLI. Run red-team evaluations, check vulnerabilities, and review results for your AI products.
homepage: https://knowyourai.hydrox.ai
requires:
  bins:
    - node
  env:
    - KNOW_YOUR_AI_DSN
primaryEnv: KNOW_YOUR_AI_DSN
metadata: {"clawdbot":{"emoji":"πŸ›‘οΈ","requires":{"bins":["node"],"env":["KNOW_YOUR_AI_DSN"]},"primaryEnv":"KNOW_YOUR_AI_DSN"}}

Know Your AI
AI security testing and evaluation CLI by HydroxAI. Run red-team evaluations, detect jailbreak vulnerabilities, and review security scores for your AI products β€” all from the command line.
Check setup
bash node {baseDir}/scripts/doctor.mjs 

Validates your DSN configuration and tests API connectivity. Requires KNOW_YOUR_AI_DSN environment variable.
Show linked product & connection
bash node {baseDir}/scripts/target.mjs 


List evaluations and datasets
bash node {baseDir}/scripts/list.mjs 


Run an evaluation
bash node {baseDir}/scripts/evaluate.mjs node {baseDir}/scripts/evaluate.mjs --max-prompts 5 node {baseDir}/scripts/evaluate.mjs --timeout 300 

Triggers an evaluation run and streams real-time progress. Returns scores, pass/fail counts, and the run ID.
Options
  • --max-prompts : Maximum prompts per dataset (default: 3)
    • 

  • --timeout : Maximum wait time in seconds (default: 600)
    • 

  • --debug: Enable debug logging
    • View run history
    bash node {baseDir}/scripts/history.mjs node {baseDir}/scripts/history.mjs --all 
    

  • --all / -a: Show all runs (default: last 10)
    • View results of a specific run
    bash node {baseDir}/scripts/result.mjs 
    

    Describe an evaluation
    bash node {baseDir}/scripts/describe.mjs 
    
Shows detailed evaluation configuration: judge model, threshold, linked datasets, and prompt counts.
    Notes
  • Requires node (>=18) runtime
    • 

  • Requires KNOW_YOUR_AI_DSN environment variable from the Know Your AI dashboard (Settings β†’ API Keys)
    • 

  • DSN format: https://kya_xxx:da2-xxx@host/product_id
    • 

  • Short alias kya is also available if installed globally via npm
    • 

  • Use doctor first to verify connectivity before running evaluations
    • 

  • Review detailed results in the Know Your AI dashboard after runs complete
    •

    βš™οΈ Configuration

  • --max-prompts : Maximum prompts per dataset (default: 3)
  • --timeout : Maximum wait time in seconds (default: 600)
  • --debug: Enable debug logging

    • πŸ“‹ Tips & Best Practices

  • Requires node (>=18) runtime
  • Requires KNOW_YOUR_AI_DSN environment variable from the Know Your AI dashboard (Settings β†’ API Keys)
  • DSN format: https://kya_xxx:da2-xxx@host/product_id
  • Short alias kya is also available if installed globally via npm
  • Use doctor first to verify connectivity before running evaluations
  • Review detailed results in the Know Your AI dashboard after runs complete
    • ```