Authentication Enforcement

Organization

RedHatProductSecurity

authentication-enforcement

Enforce authentication and authorization at the API gateway for AI systems. Use when designing, building, or reviewing API gateways that front inference engines, LLM APIs, or AI model endpoints.

Overview

Publisher	RedHatProductSecurity
Repository	`prodsec-skills`
Skill name	`authentication-enforcement`
Stars	56
Forks	9
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by RedHatProductSecurity on GitHub. Read the source before you install it.

Installation

Install the Authentication Enforcement AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/RedHatProductSecurity/prodsec-skills/tree/main/module/skills/authentication-enforcement
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/RedHatProductSecurity/prodsec-skills/tree/main/module/skills/authentication-enforcement

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/RedHatProductSecurity/prodsec-skills.git /tmp/prodsec-skills
mkdir -p .claude/skills
cp -r /tmp/prodsec-skills/module/skills/authentication-enforcement .claude/skills/authentication-enforcement

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Authentication Enforcement in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Authentication Enforcement on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Authentication Enforcement is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Authentication Enforcement at the API Gateway

Security Requirement

AI model APIs MUST require that all principals (humans and applications) are identified, authenticated, and authorized before requests reach the models. The API gateway is the primary enforcement point for this control.

AI software MUST implement a robust standard authentication mechanism or require integration with an identity provider by default. Reducing this security posture should only be an option the user explicitly chooses, never the default.

What Is Not Acceptable as Default

No authentication at all (even for internal-only APIs)
A single shared API key for all users
An empty API key
API key-only authentication without IdP integration

These approaches may seem to "facilitate use" but are not acceptable for cloud services and should not be the default for products.

Required Controls

Control	Details
Authentication	Standard protocol (OAuth 2.1/OIDC) via IdP integration
Authorization	Verify the authenticated principal has permission for the requested operation
Identity	Every request must be attributable to a specific principal

Architectures Without an API Gateway

If the AI software architecture or platform does not include an API gateway, these security controls MUST be implemented by other components:

Check if the inference engine has standard, well-known authentication mechanisms
Verify the inference engine can identify and authenticate principals securely
Ensure rate limiting and input validation are handled at the inference engine level
Document the compensating controls and their limitations

Implementation Checklist

Deploy an API gateway in front of all AI model endpoints
Configure the API gateway to require authentication by default
Integrate with an OIDC Identity Provider for authentication
Implement authorization checks based on principal identity
Ensure every request is logged with the authenticated principal's identity
If no API gateway: verify inference engine implements equivalent controls
Verify that the default configuration requires authentication (not opt-in)

Frequently asked questions

What does the Authentication Enforcement AI skill do?

Enforce authentication and authorization at the API gateway for AI systems. Use when designing, building, or reviewing API gateways that front inference engines, LLM APIs, or AI model endpoints.

Why use Authentication Enforcement on TypingMind?

Because you install it once and use it with any model. Authentication Enforcement is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Authentication Enforcement in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RedHatProductSecurity/prodsec-skills/tree/main/module/skills/authentication-enforcement. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Authentication Enforcement?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Authentication Enforcement?

As many as you like. As long as a model supports skills, you can use Authentication Enforcement with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Authentication Enforcement AI skill free?

Yes. It is published on GitHub by RedHatProductSecurity under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Debugging

openclaw

OrganizationPopular

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Openclaw Docker E2e Authoring

openclaw

OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

Openclaw Ghsa Maintainer

openclaw

OrganizationPopular

Inspect, patch, validate, publish, or confirm OpenClaw GHSA security advisories and private-fork state.

Openclaw Live Updater

openclaw

OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Authentication Enforcement at the API Gateway

Security Requirement

What Is Not Acceptable as Default

Required Controls

Architectures Without an API Gateway

Implementation Checklist

Frequently asked questions

Related AI Skills

Set up your own AI workspace now