This plugin automatically screens user-submitted comments for harmful or abusive content using the OpenAI Moderation API. It is designed for site administrators who want to maintain a respectful online environment without manually reviewing every post.

• AI-Powered Moderation: Uses the OpenAI Moderation API to analyze comment text against a range of content categories, such as hate speech, harassment, and self-harm.
• Configurable Blocking: Administrators can select which specific content classifications should be blocked, allowing for customized moderation policies.
• Pre-Save Filtering: Comments are analyzed before they are saved to the database. If flagged, the comment is not posted and the user receives an error message.
• Simple Setup: Requires only an OpenAI API key for configuration. The plugin can be enabled or disabled from a dedicated settings page within the admin area.
• Extensible Design: Built to allow developers to extend its functionality to moderate other forms of user-submitted content, like forum posts or contact form entries, using standard platform hooks.