add-ai-protection

Redirects users to the unified arcjet skill for AI endpoint security protection.

1|Updated Apr 8, 2026

Search Tags:#rate limiting #migration #deprecated #ai security #prompt injection #arcjet #pii blocking

One-click install

npx skills add https://github.com/arcjet/arcjet-plugin --skill add-ai-protection-arcjet

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: add-ai-protection
Source: https://github.com/arcjet/arcjet-plugin/tree/main/plugins/arcjet/skills/add-ai-protection
Command: npx skills add https://github.com/arcjet/arcjet-plugin --skill add-ai-protection-arcjet

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? This Skill previously added Arcjet security protection to AI/LLM endpoints and non-HTTP code paths, but it is now deprecated and exists only to redirect users to the unified `arcjet` skill that covers the same workflows. ## Core Features & Use Cases - Deprecation Notice: Clearly marks this skill as replaced by the unified `arcjet` skill. - Migration Guidance: Points users to the skill covering HTTP route protection, AI/LLM endpoints, tool calls, MCP handlers, and queue workers. - Use Case: If you previously used this skill to add prompt injection detection, PII blocking, or token budget rate limiting, switch to the `arcjet` skill for the same capabilities in one place. ## Quick Start Use the arcjet skill instead of this deprecated skill to add security protection to your AI endpoints and non-HTTP code paths.

Frequently Asked Questions about add-ai-protection

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

FAQPage Schema

How do I add Arcjet protection to AI and LLM endpoints?▼

Use the unified arcjet skill instead of this deprecated add-ai-protection skill. It covers prompt injection detection, PII blocking, and token budget rate limiting for AI/LLM endpoints and other code paths.

What replaced the add-ai-protection skill?▼

The unified arcjet skill replaced it. That single skill covers HTTP route protection including AI/LLM endpoints plus non-HTTP code paths such as tool calls, MCP handlers, and queue workers.

Is the add-ai-protection skill still supported?▼

No, this skill is deprecated and marked internal. Its documentation instructs users to switch to the arcjet skill, which provides the same protection capabilities in a unified workflow.

Does this skill protect non-HTTP code paths like queue workers?▼

This deprecated skill only redirects to the arcjet skill, which handles non-HTTP code paths including tool calls, MCP handlers, and queue workers alongside HTTP route protection.