[PR #1240] [CLOSED] add xiangxinai guardrails plugin #1480

New Issue

2026-02-22T17:59:14-05:00

yindo commented

2026-02-22 17:59:14 -05:00

📋 Pull Request Information

Original PR: https://github.com/langgenius/dify-plugins/pull/1240
Author: @ThomasLWang
Created: 9/15/2025
Status: ❌ Closed

Base: main ← Head: main

📝 Commits (7)

4d0aeaa add xiangxinai plugin
7e7c9c9 update README
0c19391 Merge branch 'langgenius:main' into main
5f84119 Update plugin according to dify team's feedback.
edd5982 Update plugin according to dify team's feedback.
f31076a Delete xiangxinai/dify-plugin-xiangxin-guardrails.difypkg
a5c1421 update xiangxin-plugin

📊 Changes

2 files changed (+0 additions, -0 deletions)

View changed files

➕ xiangxinai/dify-plugin-xiangxin-guardrails.difypkg (+0 -0)
➕ xiangxinai/xiangxin-guardrails.difypkg (+0 -0)

📄 Description

Metadata

Plugin Author: xiangxinai
Plugin Name: xiangxin-guardrails
Repository URL: https://github.com/xiangxinai/dify-plugin-xiangxin-guardrails

Submission Type

New plugin submission
Version update for existing plugin

Description

This plugin integrates XiangxinAI Security Guardrails into Dify workflows to provide comprehensive AI content safety protection. The plugin offers real-time detection capabilities for
both input prompts and AI model responses, protecting against prompt injection attacks, jailbreak attempts, and content safety violations based on Chinese cultural context and
values.

Key Features:

Open Source and Free: Apache 2.0 license, both for guardrails model and platform
Prompt Attack Detection: Based on OWASP TOP 10 LLM Applications, detects direct/indirect prompt injection, jailbreak attempts, adversarial attacks, and MCP tool poisoning
Content Safety Compliance: Implements GB/T45654—2025 standards for AI-generated content safety in Chinese context, covering political sensitivity, illegal content, violence, adult
content, and value-oriented risks
Dual Inspection Mode: Validates both user inputs (check_prompt) and AI responses (check_response_ctx) to ensure comprehensive protection
Flexible Response Actions: Supports blocking, substitution, or pass-through based on risk assessment levels
Enterprise-Grade Security: Provides complete content filtering suitable for production deployment

The plugin uses the XiangxinAI Python SDK (version ≥ 2.0.0) to interface with XiangxinAI's security services, offering free API access for developers and supporting both cloud and
on-premises deployment scenarios.

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

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

Privacy Protection Information

This plugin processes user input content and AI responses for security analysis. All content is transmitted securely to XiangxinAI's security analysis endpoints via HTTPS. The plugin:

Only processes content for security analysis purposes
Does not store or retain user content beyond the analysis request
Provides transparent risk assessment results
Supports enterprise privacy requirements through optional on-premises deployment
Complies with data protection standards for AI content security applications

The XiangxinAI Security Guardrails service operates under strict privacy protocols and provides enterprise-grade data protection suitable for sensitive business environments.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/langgenius/dify-plugins/pull/1240 **Author:** [@ThomasLWang](https://github.com/ThomasLWang) **Created:** 9/15/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (7) - [`4d0aeaa`](https://github.com/langgenius/dify-plugins/commit/4d0aeaacbe1c2d3aeeb6ecc800ab35d8e7f37c41) add xiangxinai plugin - [`7e7c9c9`](https://github.com/langgenius/dify-plugins/commit/7e7c9c902a4b61ed24841b6b57bc2eaf59d0e30c) update README - [`0c19391`](https://github.com/langgenius/dify-plugins/commit/0c1939195df0b42dc6ede08303f70b49cf99dfbf) Merge branch 'langgenius:main' into main - [`5f84119`](https://github.com/langgenius/dify-plugins/commit/5f84119a6a65a6b2865fbd2693d68a5535eb514c) Update plugin according to dify team's feedback. - [`edd5982`](https://github.com/langgenius/dify-plugins/commit/edd5982d1e858e774b3e6e91e639b52db231e265) Update plugin according to dify team's feedback. - [`f31076a`](https://github.com/langgenius/dify-plugins/commit/f31076aa40ece16d4e3b0ffb399a0f804f06d589) Delete xiangxinai/dify-plugin-xiangxin-guardrails.difypkg - [`a5c1421`](https://github.com/langgenius/dify-plugins/commit/a5c142135ac9b625283cb70c5c2a250537e26ad1) update xiangxin-plugin ### 📊 Changes **2 files changed** (+0 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `xiangxinai/dify-plugin-xiangxin-guardrails.difypkg` (+0 -0) ➕ `xiangxinai/xiangxin-guardrails.difypkg` (+0 -0) </details> ### 📄 Description 1. Metadata - Plugin Author: xiangxinai - Plugin Name: xiangxin-guardrails - Repository URL: https://github.com/xiangxinai/dify-plugin-xiangxin-guardrails 2. Submission Type - New plugin submission - Version update for existing plugin 3. Description This plugin integrates XiangxinAI Security Guardrails into Dify workflows to provide comprehensive AI content safety protection. The plugin offers real-time detection capabilities for both input prompts and AI model responses, protecting against prompt injection attacks, jailbreak attempts, and content safety violations based on Chinese cultural context and values. Key Features: - Open Source and Free: Apache 2.0 license, both for guardrails model and platform - Prompt Attack Detection: Based on OWASP TOP 10 LLM Applications, detects direct/indirect prompt injection, jailbreak attempts, adversarial attacks, and MCP tool poisoning - Content Safety Compliance: Implements GB/T45654—2025 standards for AI-generated content safety in Chinese context, covering political sensitivity, illegal content, violence, adult content, and value-oriented risks - Dual Inspection Mode: Validates both user inputs (check_prompt) and AI responses (check_response_ctx) to ensure comprehensive protection - Flexible Response Actions: Supports blocking, substitution, or pass-through based on risk assessment levels - Enterprise-Grade Security: Provides complete content filtering suitable for production deployment The plugin uses the XiangxinAI Python SDK (version ≥ 2.0.0) to interface with XiangxinAI's security services, offering free API access for developers and supporting both cloud and on-premises deployment scenarios. 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 This plugin processes user input content and AI responses for security analysis. All content is transmitted securely to XiangxinAI's security analysis endpoints via HTTPS. The plugin: - Only processes content for security analysis purposes - Does not store or retain user content beyond the analysis request - Provides transparent risk assessment results - Supports enterprise privacy requirements through optional on-premises deployment - Complies with data protection standards for AI content security applications The XiangxinAI Security Guardrails service operates under strict privacy protocols and provides enterprise-grade data protection suitable for sensitive business environments. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

yindo added the pull-request label 2026-02-22 17:59:14 -05:00

yindo closed this issue

2026-02-22 17:59:17 -05:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: langgenius/dify-plugins#1480