a6-plugin-ai-content-moderation

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

1|2|Updated Mar 6, 2026

Search Tags:#plugins #apisix #a6 #content-policy #ai-content-moderation #aws-comprehend #aliyun-moderation

Ready to run

npx skills add https://github.com/api7/a6 --skill a6-plugin-ai-content-moderation-api7

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: a6-plugin-ai-content-moderation
Source: https://github.com/api7/a6/tree/main/skills/a6-plugin-ai-content-moderation
Command: npx skills add https://github.com/api7/a6 --skill a6-plugin-ai-content-moderation-api7

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

APISIX users need a reliable way to filter harmful content from LLM prompts and responses before they reach downstream systems. This skill provides integrated configuration for AWS Comprehend and Aliyun Moderation Plus plugins via the a6 CLI, ensuring content policies are enforced at the edge.

Core Features & Use Cases

AWS moderation: configure ai-aws-content-moderation to block toxic input before it reaches the LLM.
Aliyun moderation: support request and response moderation with ai-aliyun-content-moderation, including optional streaming, integrated with ai-proxy.
Policy control: fine-tune thresholds, per-category rules, and risk levels to align with business policies.

Quick Start

Deploy a route that uses ai-aws-content-moderation or ai-aliyun-content-moderation to enforce content safety on incoming requests.

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 filter harmful content from LLM prompts in APISIX?▼

To filter harmful content from LLM prompts in APISIX, configure AI content moderation plugins like ai-aws-content-moderation or ai-aliyun-content-moderation on your routes to block toxic input before it reaches downstream LLMs.

Can I use AWS Comprehend for APISIX request moderation?▼

Yes, you can use AWS Comprehend for APISIX request moderation by configuring the ai-aws-content-moderation plugin to intercept and block toxic input before it reaches the LLM.

Does APISIX support Aliyun content moderation with streaming responses?▼

Yes, APISIX supports Aliyun content moderation with streaming responses by integrating the ai-aliyun-content-moderation plugin with ai-proxy to moderate both requests and responses dynamically.

How do I configure content policy thresholds in APISIX?▼

You configure content policy thresholds in APISIX by fine-tuning risk levels and per-category rules within the AI content moderation plugin settings to align with your specific business policies.

What is the best way to secure chat endpoints in APISIX using AI moderation?▼

The best way to secure chat endpoints in APISIX is deploying routes with ai-aws-content-moderation or ai-aliyun-content-moderation to enforce content safety on incoming requests and outgoing LLM responses.

Do I need the ai-proxy plugin to moderate LLM responses in APISIX?▼

Yes, integrating the ai-proxy plugin is required for Aliyun response moderation in APISIX, enabling the ai-aliyun-content-moderation plugin to process both requests and streaming responses.