skills.rest
moonming
moonmingCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

a6-plugin-ai-content-moderation

Configures APISIX AI content moderation plugins for LLM request and response filtering.

1|2|Updated Mar 6, 2026
Search Tags:#ai security#content moderation#plugin configuration#aliyun#llm safety#aws comprehend
One-click install
npx skills add https://github.com/moonming/a6 --skill a6-plugin-ai-content-moderation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: a6-plugin-ai-content-moderation
Source: https://github.com/moonming/a6/tree/main/skills/a6-plugin-ai-content-moderation
Command: npx skills add https://github.com/moonming/a6 --skill a6-plugin-ai-content-moderation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill safeguards LLM applications by filtering harmful or inappropriate content in both user requests and AI responses, ensuring safer and more compliant interactions.

Core Features & Use Cases

  • Request Moderation: Blocks toxic content before it reaches the LLM using AWS Comprehend or Aliyun.
  • Response Moderation: Filters harmful content from LLM outputs (Aliyun only).
  • Configurable Thresholds: Fine-tune sensitivity for different content categories.
  • Use Case: Protect your chatbot from offensive user input and prevent your AI from generating inappropriate responses by integrating content moderation directly into your API gateway.

Quick Start

Configure the a6 route to use the ai-aws-content-moderation plugin with specific hate speech and violence thresholds.

Frequently Asked Questions about a6-plugin-ai-content-moderation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure content moderation for LLM requests in APISIX?▼

To configure content moderation in APISIX, set up the ai-aws-content-moderation or ai-aliyun-content-moderation plugins on your route to filter harmful content in LLM requests. You can specify moderation categories and risk levels to block toxic input.

Can I filter harmful content from LLM responses as well as requests?▼

Yes, response moderation filters harmful content generated by the LLM. This feature is currently supported by the ai-aliyun-content-moderation plugin, ensuring your AI outputs remain compliant and safe.

What is the difference between AWS Comprehend and Aliyun for AI content moderation?▼

AWS Comprehend supports request moderation to block toxic input before reaching the LLM. Aliyun supports both request and response moderation, allowing you to filter inappropriate content generated by the AI as well.

How do I fine-tune sensitivity thresholds for hate speech and violence?▼

You fine-tune sensitivity by configuring specific moderation categories and risk levels within the APISIX plugin configuration. This allows you to set distinct thresholds for hate speech and violence based on your application's safety requirements.

Does APISIX content moderation support streaming mode for LLM interactions?▼

Yes, the APISIX AI content moderation plugins support streaming modes. This allows you to filter harmful content in both user requests and AI responses during real-time, streaming LLM interactions.

When do I need LLM content moderation at the API gateway layer?▼

You need LLM content moderation at the API gateway layer when you want to safeguard chatbot applications by intercepting offensive user input and preventing inappropriate AI responses before they reach the end user.

Related Skills

Explore More Software Engineering Skills→
koderoverkoderover
7

apisix

Manage Apache APISIX routes, upstreams, services, and plugins via the Admin API.

Official
Intermediate
JansenAnalyticsJansenAnalytics
5

error-monitor

Monitor application logs and stderr to detect errors, crashes, and exceptions.

Community
Intermediate
api7api7
1

a6-plugin-ai-content-moderation

Configure AWS Comprehend or Aliyun content moderation plugins for APISIX routes.

Official
Advanced
moonmingmoonming
1

a6-plugin-ai-prompt-decorator

Configure the Apache APISIX ai-prompt-decorator plugin to prepend and append LLM messages.

Community
Intermediate