---
title: What safety controls are available?
description: "Block harmful content, hide personal info (PII redaction) in replies, and stay-on-topic rules with allowed and blocked topic lists. Advanced settings include prompt injection detection (Off, Standard, Strict), output toxicity filter, content moderation level, hallucination guard, max input tokens, rate…"
url: "https://www.smsgatewaycenter.com/blog/kb/what-safety-controls-are-available/"
updated: "2026-07-31"
category: AI Agent Builder / Safety
---

# What safety controls are available?

Block harmful content, hide personal info (PII redaction) in replies, and stay-on-topic rules with allowed and blocked topic lists. Advanced settings include prompt injection detection (Off, Standard, Strict), output toxicity filter, content moderation level, hallucination guard, max input tokens, rate limit per user, cooldown seconds, max messages per session, competitor mention rules, PII leakage check on output, and brand tone check.

### More Related Articles

- [What is “Stay on topic” and when should I use it?](https://www.smsgatewaycenter.com/blog/kb/what-is-stay-on-topic-and-when-should-i-use-it/)
- [Can I customize what customers see when the bot cannot help?](https://www.smsgatewaycenter.com/blog/kb/can-i-customize-what-customers-see-when-the-bot-cannot-help/)

Found this useful?[Add as Preferred Source on Google](https://www.google.com/preferences/source?q=smsgatewaycenter.com)