Copilot SecuritySAFE
✨ A customizable copilot-instructions.md ruleset & prompts to guide GitHub Copilot toward secure coding defaults in Java, Node.js, C# and Python. Blocks risky patterns, teaches safe habits.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/1a935343-666d-457a-b210-2e0d27e9ef81)
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/andskills/for repeatable AppSec workflows inside Copilot. - An installable GitHub Copilot CLI plugin under
plugins/copilot-securityfor reusable AppSec agents and skills across projects. - 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 implemen
61f82ec69cb3OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add copilot-instructions-mcp -- npx -y [email protected]
{
"mcpServers": {
"copilot-instructions-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_prompt | read | |
list-prompts | read | |
list_resources | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
streamable-http
.gitlab-ci.yml
.markdownlint.yml
.markdownlintignore
@modelcontextprotocol/sdk, amqplib, dotenv, express, express-rate-limit, mysql2, sequelize, ulid
You are a senior software engineer performing a **multi-stage review of application behavior and business logic flow**.
You are a senior application security engineer helping developers review and harden a web application’s Content Security Policy (CSP).
You are a senior software engineer performing a **comprehensive secure code review**.
Gates applied: no_behavioural_pass.
61f82ec69cb3full audit observations/trust-audit/mcp-server/robotti-io__copilot-security.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 61f82ec69cb3 | SAFE | B | 89 | first audit |
Questions
What is the Copilot Security MCP server?
✨ A customizable copilot-instructions.md ruleset & prompts to guide GitHub Copilot toward secure coding defaults in Java, Node.js, C# and Python. Blocks risky patterns, teaches safe habits.
What tools does Copilot Security expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Copilot Security safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Copilot Security need?
No credential environment variables were found in its source, so it appears to need none.
How does Copilot Security run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as copilot-instructions-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (61f82ec69cb3), read on 2026-10-08. The repository is watched and re-audited when it changes.