PlugWiki

google-cloud-waf-security Skill: GCP Security Review

Makes Claude assess a Google Cloud workload against the Well-Architected Framework security pillar and suggest prioritized fixes.

Installs
15.1K
on skills.sh
Stars
21.8K
on GitHub
Files
1
besides SKILL.md
Updated
Nov 2026
last repo commit

google-cloud-waf-security makes Claude interview you about your workload, then compare it with the security pillar of the Google Cloud Well-Architected Framework. It follows five steps: understand the context, find gaps, recommend, explain, and refine.

The skill is advice only. It bundles no scripts, but its attribution file covers any gcloud, REST or MCP commands Claude does run. It comes from Google's skills repo.

Good for

  • Cloud architects reviewing a Google Cloud design
  • Security teams checking IAM, network and data controls
  • Teams securing AI workloads on Google Cloud

Install google-cloud-waf-security

Claude Code

  1. 1

    Copy this prompt.

    Install the google-cloud-waf-security skill in Claude Code. Run this command:

npx skills add https://github.com/google/skills --skill google-cloud-waf-security

Then check that it loaded and tell me how to use it.
  2. 2

    Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

From its listing on skills.sh. Source.

What's in the skill

When it loads

Generates security-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Google Cloud Well-Architected Framework (WAF). Use this skill to evaluate workloads, identify security requirements, and provide actionable recommendations for IAM, network security, data protection, and operational security.

Sections in SKILL.md

  1. Attribution
  2. Overview
  3. Workflow
  4. Core principles
  5. Relevant Google Cloud products
  6. Workload assessment questions
  7. Validation checklist

Key facts

Author
google (repo owner)
Repo
google/skills
Installs on skills.sh
15,122
Repo stars
21,764
License
Apache-2.0
Last repo commit
2026-11-01
Files in the skill folder
2 files including SKILL.md

What it includes

  • Five steps from context questions to refined advice

    Ask targeted questions, evaluate against the principles and checklist, give prioritized recommendations with products, explain the benefit, then iterate.

    Workflow

  • Eight principles, from security by design to shared responsibility

    Security by design, zero trust, shift-left, preemptive cyber defense, using AI securely, using AI for security, regulatory, compliance and privacy needs, and shared responsibilities and shared fate. Each names a grounding document.

    Core principles

  • Examples by area

    Groups products under identity and access, network security, data security, security operations, and automation and supply chain.

    Relevant Google Cloud products

  • A question bank per principle

    Claude picks the questions that fit your situation.

    Workload assessment questions

  • Yes-or-no checks per principle

    Five groups of checks (security by design, zero trust, shift-left, preemptive cyber defense, AI security and governance), used to spot missing controls, such as default networks still enabled or no VPC Service Controls around sensitive data.

    Validation checklist

  • Usage tag rules for gcloud, REST and MCP commands

    Applies only if Claude runs such commands.

    Runs code · references/attribution.md

From the official docs

Permissions

Low risk

The skill gives security advice and bundles no scripts. If Claude runs gcloud, REST or MCP commands during a review, the attribution file adds a usage tag naming the skill.

What it can do

  • Read your data
  • Create and change things
  • Delete things
  • Read-only mode

Watch out for

  • Commands carry a usage tag

    Before any gcloud, REST or MCP command, the SKILL.md requires reading the attribution file, which tags commands with the skill name. Ask Claude to leave the tag out if you do not want it. github.com

Technical details
Talks toGoogle Cloud APIs, only if Claude runs gcloud, REST or MCP commands

Questions

What does the google-cloud-waf-security skill do?

It makes Claude assess a Google Cloud workload against the security pillar of the Well-Architected Framework and give prioritized recommendations that name specific Google Cloud products.

What does the review cover?

Eight principles: security by design, zero trust, shift-left security, preemptive cyber defense, using AI securely, using AI for security, compliance and privacy, and shared responsibilities and shared fate. Products are grouped under IAM, network, data, security operations and supply chain.

Does it scan my project automatically?

The workflow starts by asking you questions about your architecture. The SKILL.md does not describe an automated scan.

How do I install it?

Use the install box above. The folder has 2 files including SKILL.md. The google/skills README documents the skills CLI (npx skills add google/skills). Its plugin routes install separate Google product plugins, not this skill.

Is it safe to install?

It bundles no scripts. It mostly produces advice. If Claude runs gcloud or other commands, a usage tag naming the skill is added, and you can ask for it to be left out.

How is it different from cloud-sql-basics?

cloud-sql-basics is a how-to for creating and managing Cloud SQL. This skill reviews any workload against the security pillar. Both come from google/skills.

Information

updated Nov 2, 2026

Repository
google/skills
Folder
skills/cloud/google-cloud-waf-security

google/skillsskills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 2
  1. google-cloud-waf-security SKILL.md · github.com
  2. attribution.md · github.com

Updated Nov 2, 2026.