github-security-mcp CLAUDE.md

Repository instructions for a GitHub security MCP project that gives an AI agent access to GitHub security information and analysis tasks.

In plain words
What is it for?
Use them when developing this project so its security-analysis goals and intended checks remain clear.
Why use it?
They define the project's purpose and the security areas to inspect, such as organizations, repositories, workflows, secrets, and dependencies.

Instructions file

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/badchars/github-security-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/badchars/github-security-mcp
Per session 1,080 This file is loaded in full into every session.
When invoked 1,080 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 $0.01080 $0.01080
Opus 5 $0.00540 $0.00540
Sonnet 5 $0.00216 $0.00216
Haiku 4.5 $0.00108 $0.00108

Measured 2d ago against content hash 99bbe2363196, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-security-mcp CLAUDE.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 2d 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.

CLAUDE.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Security MCP

Project Context

Bu proje hackbrowser-mcp (browser security testing) ve cloud-audit-mcp (AWS/Azure/GCP misconfig detection) sonrasında üçüncü MCP projesi. GitHub'ın Enterprise Security özelliklerini open-source MCP olarak sunacak — AI agent'a GitHub API'lerini vererek organization, repository, workflow, secret, dependency güvenlik analizi yapacak.

Neden Bu MCP?

GitHub Advanced Security (GHAS) Enterprise lisans gerektirir. Secret scanning, code scanning, Dependabot gibi özellikler var ama hepsi GitHub UI'da. Hiçbiri AI agent'a MCP üzerinden kontrol vermiyor. Fark: GHAS'ı açarsın dashboard'dan bakarsın. Bu MCP'de agent direkt GitHub API'lerini çağırır, org/repo/workflow security posture'unu analiz eder, attack path'leri bulur, fix önerir.

Hedef Kullanım

User: "GitHub organizasyonumdaki en kritik 5 security issue'yu bul"

Agent: → Org settings'i kontrol eder (2FA, SSO, member privileges)
       → Repo'ları tarar (branch protection, secret scanning, code scanning)
       → Workflow'ları analiz eder (injection, unpinned actions, over-permissive GITHUB_TOKEN)
       → Bulguları severity'ye göre sıralar
       → Her biri için fix komutu/config verir

Taranacak Alanlar

Organization Security:

  • 2FA enforcement
  • SSO/SAML configuration
  • Member privileges (repo creation, forking, visibility defaults)
  • Outside collaborators audit
  • OAuth app / GitHub App installations
  • IP allowlists
  • Audit log patterns

Repository Security:

  • Branch protection rules (require reviews, signed commits, admin bypass)
  • CODEOWNERS enforcement
  • Secret scanning enabled + alerts
  • Code scanning (CodeQL) enabled + alerts
  • Dependabot enabled + security alerts
  • Security policy (SECURITY.md)
  • Private vulnerability reporting
  • Deploy keys audit
  • Webhook security (insecure URLs, exposed secrets)
  • Fork settings (allow fork, fork visibility)

GitHub Actions Security:

  • Workflow injection (untrusted inputs: github.event.*, run:)
  • pull_request_target + checkout PR head = arbitrary code execution
  • Unpinned actions (tag vs SHA pinning)
  • GITHUB_TOKEN default permissions (read-all vs least-privilege)
  • Self-hosted runner exposure
  • Environment protection rules
  • Fork PR workflow approval settings
  • Reusable workflow trust
  • Artifact upload/download security
  • OIDC for cloud deployments

Read the full file on GitHub · 111 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. 2d ago First seen · 111 lines · 1,080 tokens per session scan A 99bbe2363196

Subscribe to this mod's changes

github-security-mcp CLAUDE.md is an instructions file published in the GitHub repository badchars/github-security-mcp (12 stars, last pushed 5mo ago), licensed MIT. It adds 1,080 tokens to every session, about $0.0054 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.