🛡️ Copilot Security Instructions

A comprehensive toolkit to guide GitHub Copilot toward secure coding practices. This project includes customizable instructions and security-focused prompts to help development teams identify and mitigate security risks effectively.

Designed for security-conscious teams, this configuration ensures Copilot suggests safer code patterns, avoids common vulnerabilities, and reinforces best practices — all without disrupting your workflow.

🔐 What's Inside

This project offers:

• Secure-by-default guidance for all languages (e.g., input validation, secret handling, safe logging).
• Language-specific secure patterns:
  • ☕ Java
  • 🟩 Node.js
  • 🟦 C#
  • 🐍 Python
• "Do Not Suggest" lists to block risky Copilot completions (e.g., eval, inline SQL, insecure deserialization).
• AI hallucination protections to prevent package spoofing, non-existent APIs, and misinformation risks.
• Mentorship-style tips to help newer engineers build secure coding habits.
• Custom agents & Agent Skills under agents/ and skills/ for repeatable AppSec workflows inside Copilot.
• An MCP server for seamless integration of these prompts into other projects.

🗂️ Prompt Catalogue

Explore the available prompts and their intended use cases:

These prompt files live under prompts/ in this repo and are intended to be copied into a consuming repository’s .github/prompts/.

Recommended workflow: start with the application-security-orchestrator agent (see agents/application-security-orchestrator.agent.md).
It standardizes intake, then hands off to specialist agents (Analyst/Architect/Engineer) depending on whether you want findings, a threat model, or implemented fixes.

🧑‍💻 Agents

🧩 Skills

📦 How to Use in a Real Project

Tip for contributors: when adding a file under prompts/, update the Prompt Catalogue table.

Leveraging Static Files

1. Copy the copilot-instructions.md file into your repo under:
   .github/copilot-instructions.md

2. Drop the prompts you want into:
   .github/prompts/

3. Open the prompt you wish to run within your IDE

4. Click the Run Prompt button to the top-right of the file

   

   ℹ️ Note: If you don't see the run prompt button; check to make sure the Chat: Prompt Files functionality is enabled in your settings
   

Leveraging the MCP Server

The MCP server simplifies the integration of secure coding prompts into your workflow. Follow these steps:

Run MCP from source

1. Install dependencies

   npm install
   

2. Setup environment

   cp .env.example .env
   

   The MCP server reads configuration from a .env file. Customize the following variables as needed:

   Variable	Description	Default
   server.port	Port the MCP server listens on.	8080
   server.ssl	Whether to use ssl for express server	false
   server.ssl.pfx	Path to pfx file	localhost.pfx
   server.ssl.pfx.passphrase	Passphrase for pfx file	PFX_PASSPHRASE
   server.hostname	Hostname the server binds to.	localhost
   logger.transports.console.enabled	Enable console logging output.	false
   logger.transports.console.level	Log level for console output.	info
   logger.transports.amqp.enabled	Enable AMQP-based logging.	false
   logger.transports.amqp.level	Log level for AMQP transport.	http
   logger.transports.amqp.hostname	Hostname of the AMQP broker.	localhost
   logger.transports.amqp.port	Port for the AMQP broker.	5672
   logger.transports.amqp.username	Username for AMQP authentication.	guest
   logger.transports.amqp.password	Password for AMQP authentication.	guest
   logger.transports.amqp.exchange	Exchange name used for AMQP logging.	logs
   logger.transports.amqp.vhost	Virtual host for AMQP logging.	/logs
   logger.transports.amqp.heartbeat	Heartbeat interval in seconds.	60
   logger.transports.amqp.locale	Locale for the AMQP connection.	en_US
   logger.transports.amqp.type	AMQP exchange type.	direct
   logger.transports.amqp.durable	Whether the AMQP exchange is durable.	false

3. Start the server

   npm start
   

Run MCP in Docker

1. Build docker container

   docker build -t copilot-security-mcp .
   

2. Run docker container

   docker run -d -p 8080:8080 copilot-security-mcp
   

Configuring VSCode for MCP

1. Open VSCode and run the MCP: Open User Configuration command.

2. Add the following JSON configuration:

   {
      "servers": {
         "copilot-instructions-mcp": {
            "url": "http://localhost:8080/mcp"
         }
      }
   }
   

3. Save the configuration.

4. Navigate to the Extensions menu in VSCode.

5. Locate the copilot-instructions-mcp server, click the settings cog, and select start server.

Using MCP with GitHub Copilot

1. Open GitHub Copilot Chat.

2. Ask it to run any of the prompts against your repository or specific files.

   Example: Please get and run the secure code review prompt.

📚 Languages Supported

• ☕ Java — Spring, Jakarta, JDBC, OWASP Encoder
• 🟩 Node.js — Express, pg, mongoose, helmet, ajv, zod
• 🟦 C# — ASP.NET Core, Razor, ADO.NET, Entity Framework
• 🐍 Python — Flask, Django, SQLAlchemy, pydantic, Jinja2, bcrypt, cryptography

🛠️ Development

Use these npm scripts to work on the project:

Recommended workflow: Run npm run lint (and npm run lint:fix if needed) before committing or opening a PR.

📣 Feedback & Contributions

This project is community-friendly and designed for continuous improvement.
If you have suggestions, feedback, or language rules to contribute — feel free to open an issue or PR.

Let’s make Copilot safer, one suggestion at a time. 🛠️

Disclaimer

This repository, including all instructions, prompts, agents, examples, and related application content,
is provided “AS IS”, without warranties or conditions of any kind, express or implied, including without
limitation warranties of merchantability, fitness for a particular purpose, noninfringement, security,
accuracy, completeness, or regulatory compliance.

Use of this repository is at your own risk. Robotti and its contributors shall not be liable for any claims,
damages, losses, or other liability arising from or related to the use, misuse, or inability to use this
repository or any outputs produced from it.