Safety Scan Scan content for prompt injection, jailbreak attempts, and unsafe patterns. When to use Before processing untrusted input (user submissions, API payloads, webhook data), scan it to detect prompt injection, adversarial content, or policy violations. Steps 1. Quick safety check — call with the input text for a boolean safe/unsafe result 2. Deep analysis — call for detailed threat classification and confidence scores 3. Full scan — call for comprehensive multi-layer scanning 4. Train defenses — call with confirmed threats to improve detection 5. View stats — call for detection rates…