No Credential Forwarding

Organization

RedHatProductSecurity

no-credential-forwarding

Prevent MCP servers from forwarding user credentials or tokens to downstream tools. Use when building, reviewing, or auditing MCP server integrations with external tools or APIs.

Overview

Publisher	RedHatProductSecurity
Repository	`prodsec-skills`
Skill name	`no-credential-forwarding`
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 No Credential Forwarding 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/no-credential-forwarding
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/no-credential-forwarding

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/no-credential-forwarding .claude/skills/no-credential-forwarding

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

Use it in TypingMind

Enable No Credential Forwarding 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 No Credential Forwarding 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 No Credential Forwarding 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.

No Credential Forwarding in MCP Servers

Security Requirement

MCP servers MUST NOT forward any credentials or authentication tokens received from users to downstream tools or third-party APIs. This is explicitly forbidden by the MCP specification and has a high security impact.

Risks of Credential Forwarding

Token leakage: User tokens exposed to third-party services
Confused deputy attacks: Third-party services may use the user's token to access resources beyond what the MCP server intended
Excessive privilege: Downstream tools receive user-level access when they only need scoped tool-level access
Audit trail corruption: Actions performed by tools are attributed to the user instead of the MCP server

Required Approach

Instead of forwarding user tokens, MCP servers MUST obtain separate credentials for downstream services through one of:

OAuth client flows: MCP server acts as an OAuth client and initiates its own OAuth flow to obtain tokens for third-party APIs
Pre-registered service accounts: Use API keys or service accounts registered specifically for the MCP server
Token Exchange (preferred): See the token-exchange-for-tools skill for the recommended approach

Implementation Checklist

Audit all outbound requests from the MCP server to external services
Verify no user tokens are included in any outbound request headers, query parameters, or bodies
Implement separate credential management for each downstream API
Add automated tests that verify user tokens are never forwarded
Log outbound requests (excluding sensitive headers) for security audit

Anti-Pattern


# FORBIDDEN - never do this
def call_external_tool(user_token, tool_url, params):
    headers = {"Authorization": f"Bearer {user_token}"}  # WRONG
    return requests.post(tool_url, headers=headers, json=params)

Correct Pattern


# CORRECT - use MCP server's own credentials
def call_external_tool(tool_url, params):
    server_token = get_server_credential_for(tool_url)
    headers = {"Authorization": f"Bearer {server_token}"}
    return requests.post(tool_url, headers=headers, json=params)

Frequently asked questions

What does the No Credential Forwarding AI skill do?

Prevent MCP servers from forwarding user credentials or tokens to downstream tools. Use when building, reviewing, or auditing MCP server integrations with external tools or APIs.

Why use No Credential Forwarding on TypingMind?

Because you install it once and use it with any model. No Credential Forwarding 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 No Credential Forwarding in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RedHatProductSecurity/prodsec-skills/tree/main/module/skills/no-credential-forwarding. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use No Credential Forwarding?

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 No Credential Forwarding?

As many as you like. As long as a model supports skills, you can use No Credential Forwarding with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the No Credential Forwarding 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

Diagnose Gateway

openclaw

OrganizationPopular

Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.

Apple Notes

Create, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.

Bear Notes

Create, search, and manage Bear notes via grizzly CLI.

Gog

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

No Credential Forwarding in MCP Servers

Security Requirement

Risks of Credential Forwarding

Required Approach

Implementation Checklist

Anti-Pattern

Correct Pattern

Frequently asked questions

Related AI Skills

Set up your own AI workspace now