mcp-vosdroits security.instructions.md

mcp-vosdroits security.instructions.md is an instructions file for GitHub Copilot from guigui42/mcp-vosdroits. It costs 532 tokens per session, scanned A, original, MIT.

Security instructions for developing Go servers that communicate with tools or services through the MCP protocol.

In plain words
What is it for?
Use them when validating parameters and URLs, configuring HTTPS and timeouts, handling rate limits and errors, managing secrets, or protecting logs.
Why use it?
They reduce risks from untrusted inputs, unsafe network calls, exposed secrets, leaked personal data, and poorly handled failures.

Instructions file for GitHub Copilot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/guigui42/mcp-vosdroits/security
Clone the repo
git clone --depth 1 https://github.com/guigui42/mcp-vosdroits

Made for: GitHub Copilot.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-vosdroits security.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/guigui42/mcp-vosdroits/security.svg)](https://agentmods.dev/instructions/guigui42/mcp-vosdroits/security)
Your own site
<a href="https://agentmods.dev/instructions/guigui42/mcp-vosdroits/security"><img src="https://agentmods.dev/badge/instructions/guigui42/mcp-vosdroits/security.svg" alt="Measured on agentmods" height="20"></a>
Per session 532 This file is loaded in full into every session.
When invoked 532 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00532 $0.00532
Opus 5 $0.00266 $0.00266
Sonnet 5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 5d ago against content hash 228ae6536927, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-vosdroits security.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/instructions/security.instructions.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Best Practices

Input Validation

  • Validate all external inputs (tool parameters, resource URIs)
  • Use strong typing to prevent invalid states
  • Sanitize user-provided URLs and queries
  • Validate data formats (emails, URLs, etc.)
  • Set reasonable limits on input sizes

HTTP Security

Client Configuration

  • Always use HTTPS for external API calls
  • Set reasonable timeouts to prevent hanging requests
  • Validate SSL/TLS certificates
  • Handle redirects carefully

Rate Limiting

  • Implement rate limiting for external API calls
  • Handle 429 (Too Many Requests) responses gracefully
  • Use exponential backoff for retries

Error Handling

  • Don't expose sensitive information in error messages
  • Log errors securely without leaking secrets
  • Return generic error messages to clients
  • Log detailed errors for debugging

Secrets Management

  • Never hardcode secrets in source code
  • Use environment variables for configuration
  • Rotate secrets regularly
  • Don't log sensitive information
  • Use secret management services when available

Data Privacy

  • Don't log personally identifiable information (PII)
  • Sanitize logs before storage
  • Respect user privacy in caching
  • Follow data retention policies

Dependency Security

  • Regularly update dependencies
  • Use go mod tidy to remove unused dependencies
  • Scan for known vulnerabilities
  • Pin dependency versions in production

Cryptography

  • Use Go's standard library crypto packages
  • Don't implement custom cryptography
  • Use crypto/rand for random number generation
  • Use TLS for network communication

Context Security

  • Set timeouts on contexts to prevent resource exhaustion
  • Cancel contexts when operations complete
  • Don't store sensitive data in context values

Common Vulnerabilities

SQL Injection

Not applicable for this project, but if using databases, always use parameterized queries.

Path Traversal

  • Validate file paths from user input
  • Use filepath.Clean to sanitize paths
  • Restrict file access to allowed directories

Read the full file on GitHub · 102 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 102 lines · 532 tokens per session scan A 228ae6536927

Subscribe to this mod's changes

mcp-vosdroits security.instructions.md is an instructions file published in the GitHub repository guigui42/mcp-vosdroits (105 stars, last pushed 6mo ago), licensed MIT. It adds 532 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories