This project is not covered by Drupal’s security advisory policy.
Adds AI-powered validation to the editorial workflow of a Drupal CMS site. Basic page text is checked against an editorial content policy (no personal data about private individuals, no offensive language, no placeholder text) by a chat-capable AI provider, and uploads to the Image media type are checked for unsafe imagery by a vision-capable provider. Non-compliant content is rejected with a clear message to the editor before it is saved.
Built on AI Validations and Field Validation. Applies the AI image safety validation recipe for the image part. Works with any AI provider that supports the chat and chat_with_image_vision operation types.
Requires default models for both operation types to be configured before applying. See the README for setup, and for how to adjust the policy in the UI.
Project information
- Ecosystem: AI (Artificial Intelligence)
- By kotekirkitadze on , updated
This project is not covered by the security advisory policy.
Use at your own risk! It may have publicly disclosed vulnerabilities.
