// SECTION 01
AI Security Playground
Live OWASP LLM Top 10 scanner. Select categories, hit scan — semantic detection engine tests 35+ attack payloads against Claude or GPT-4 in real time.
scan_config.json
PROVIDER
MODEL
CATEGORIES (2/10)
TARGET SYSTEM PROMPT (optional)
Rate limited · 3 scans/hr
results
⚡
Configure a scan and hit Run
Results stream in real-time as each payload executes