Skip to content

Add OpenGuardrails Plugin#1446

Merged
LogicOber merged 4 commits intolanggenius:mainfrom
openguardrails:main
Nov 9, 2025
Merged

Add OpenGuardrails Plugin#1446
LogicOber merged 4 commits intolanggenius:mainfrom
openguardrails:main

Conversation

@thomas-security
Copy link
Copy Markdown
Contributor

Plugin Submission Form

1. Metadata

2. Submission Type

  • New plugin submission
  • Version update for existing plugin

3. Description

This plugin integrates OpenGuardrails into Dify workflows to provide comprehensive AI guardrails protection. The plugin offers real-time detection capabilities for both input prompts and AI model responses, protecting against prompt injection attacks, jailbreak attempts, content safety violations and senstive data leakage.

4. Checklist

  • I have read and followed the Publish to Dify Marketplace guidelines
  • I have read and comply with the Plugin Developer Agreement
  • I confirm my plugin works properly on both Dify Community Edition and Cloud Version
  • I confirm my plugin has been thoroughly tested for completeness and functionality
  • My plugin brings new value to Dify

5. Documentation Checklist

Please confirm that your plugin README includes all necessary information:

  • Step-by-step setup instructions
  • Detailed usage instructions
  • All required APIs and credentials are clearly listed
  • Connection requirements and configuration details
  • Link to the repository for the plugin source code

6. Privacy Protection Information

Based on Dify Plugin Privacy Protection Guidelines:

  1. No Collection of Personal Information
    OpenGuardrails does not collect, store, or process any personally identifiable information.

  2. Scope of Detection
    The plugin only analyzes the input and output of large language models for security and compliance purposes.

  3. No Commercial Use
    We do not sell, rent, or share any data involved in the detection process with third parties.

  4. Data Handling Principles
    All detection is performed in a secure environment and is used solely for safety analysis. The data will not be used for any other purpose.

If you have any questions or concerns about this Privacy Policy, please contact us at: thomas@OpenGuardrails.com

Data Collection

This plugin does not collect user personal data.

Privacy Policy

  • I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines

@LogicOber LogicOber self-assigned this Oct 29, 2025
@thomas-security
Copy link
Copy Markdown
Contributor Author

Hello @LogicOber ,
Please help review and approve.
Let me know if I need to update anything. Thanks!

Copy link
Copy Markdown
Contributor

@LogicOber LogicOber left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

version: 0.0.2
type: plugin
author: OpenGuardrails
name: openguardrails

Please note author must be all lowercase

@thomas-security
Copy link
Copy Markdown
Contributor Author

Hello @LogicOber ,
Thansk for review. We have updated the plugin to lower case all the authors name.
Sorry for the inconvenience and please help to review further.
Thanks.

@LogicOber LogicOber merged commit 07c3091 into langgenius:main Nov 9, 2025
2 checks passed
crazywoola pushed a commit that referenced this pull request Apr 3, 2026
Gmasterzhangxinyang pushed a commit to Gmasterzhangxinyang/dify-plugins that referenced this pull request Apr 6, 2026
… might contains incorrect context window size (langgenius#1446)

* Update context size and max_tokens for GPT-5 chat

Adjusted context_size and max_tokens in gpt-5-chat-latest.yaml based on API testing and documentation. Added comments to clarify discrepancies between documentation and actual API limits.

* Bump OpenAI plugin version to 0.2.2

Updated the manifest.yaml to reflect a new version for the OpenAI plugin. No other changes were made.

* Update gpt-5-chat-latest.yaml

* Replace isinstance checks with duck-typing in LLM

Updated type checks in OpenAILargeLanguageModel to use duck-typing instead of isinstance for tool call and function call objects. This avoids issues with generic typing classes and improves compatibility.

* Update llm.py

* Update llm.py
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants