OpenAI Moderation, Profanity, NSFW Filter

Official Plugin by Brandarrow for OpenAI Moderation, Profanity, NSFW Filter - Bubble.io Plugin

---

Vitals

Description

OpenAI Moderation by Brandarrow is a free, AI-powered content moderation plugin designed for Bubble.io applications. It leverages OpenAI’s powerful moderation API to help developers filter harmful, explicit, or unsafe content in real time promoting a safer, more ethical digital environment.

This plugin provides automatic detection of sensitive or inappropriate content, ensuring your platform remains compliant and user-friendly with minimal effort.

Price

Free

Installation

OpenAI Mod, Profanity, NSFW Plugin for BubbleBubble

Add the plugin to your Bubble app via the official plugin marketplace.

Demo & Editor

Demo Editor

---

Instructions

You can use the plugin either as a workflow action or as a data source in conditionals:

1

Workflow Action

Add the action: Brandarrow – OpenAI – Moderation Check or Brandarrow - OpenAI - Moderation Check (with Image)

Use it in any workflow where user input or data needs to be checked.

2

API Data Source

Select “Get data from an external API”

Choose: Brandarrow – OpenAI – Moderation Check or Brandarrow - OpenAI - Moderation Check (with Image)

Bind the returned data to a condition, display element, or database save logic.

That's it you are ready to use the plugin

---

Key Features

The moderation tool checks for content in the following categories:

Category	Description
Hate	Content promoting hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability, or caste.
Hate/Threatening	Hate combined with threats of violence or serious harm.
Harassment	Harassing language toward individuals or groups.
Harassment/Threatening	Harassment with threats of violence or serious harm.
Self-harm	Promotion or depiction of self-harm, such as suicide, cutting, or eating disorders.
Self-harm/Intent	Expressed intent to engage in self-harm.
Self-harm/Instructions	Encouragement or instructions for self-harm.
Sexual	Sexually explicit or arousing content (excluding educational).
Sexual/Minors	Any sexual content involving individuals under 18.
Violence	Depictions or threats of death, violence, or injury.
Violence/Graphic	Graphic, detailed depictions of violence or injury.

---

Components

Element

None

Action

• Brandarrow - OpenAI - Moderation Check

• Brandarrow - OpenAI - Moderation Check (with Image)

Event

None

Data calls

• Brandarrow - OpenAI - Moderation Check

• Brandarrow - OpenAI - Moderation Check (with Image)

---

Example Use Cases

• Flag user-submitted content in forums, reviews, or chats.

• Prevent posting of inappropriate or violent text/images.

• Enforce community guidelines and compliance requirements.

⚠️ Tip: For best accuracy, break long text inputs into smaller chunks under 2,000 characters each.

---

Common Issues & Troubleshooting

Issue	Likely Cause	Suggested Fix
No moderation data returned	Text input is too long	Split text into chunks < 2,000 characters
False positives or mismatches	Ambiguous or borderline language	Consider using context-aware conditionals
Plugin action not working in workflow	Action not connected properly	Ensure the workflow uses the “Brandarrow – OpenAI – Moderation Check” action with valid input
Conditional check shows no results	API call not triggered or returns null	Confirm the API is connected and the response is parsed properly
Plugin returns error when using an image	The URL is not publicly viewable	Install the File Sharer plugin (free) and use the result of that as the image URL input in this plugin

---

Changelog

Version	Status	Date	Notes
1.0.0	Shipped	October 3, 2024	Initial release. Full category support using OpenAI’s moderation API.
1.1.0	Shipped	July 12, 2025	Added image moderation support

---

Need Help?

Help & Support

---