gcp-security

A security-review guide for Google Cloud systems and implementations. It focuses on limiting access, protecting secrets, and addressing common web and cloud security risks.

In plain words
What is it for?
Use it to review IAM roles, service accounts, secrets, GKE identity setup, public cloud resources, Cloud Run access, and security requirements in technical designs.
Why use it?
It helps find overly broad permissions, exposed credentials, unsafe storage or endpoints, and other security gaps before development or release.

Skill for Claude CodeCodex

Part of the googlecloud-plugin plugin — 17 skills, 2 MCP servers shipped together

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 skills/jpantsjoha/googlecloud-plugin/gcp-security
Any agent
npx skills add jpantsjoha/googlecloud-plugin --skill gcp-security
Clone the repo
git clone --depth 1 https://github.com/jpantsjoha/googlecloud-plugin

Made for: Claude Code, Codex.

Or install googlecloud-plugin, the plugin that ships this one along with the rest of its 17 skills, 2 MCP servers.

Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 809 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00134 $0.00809
Opus 5 $0.00067 $0.00404
Sonnet 5 $0.00027 $0.00162
Haiku 4.5 $0.00013 $0.00081

Measured 2d ago against content hash 71a5fbea3aab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gcp-security 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.

skills/gcp-security/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GCP Security

Tier 3 — cross-cutting security enforcer. Reviews both the solution-designer output (cross-vendor security gaps) and the GCP architect's HLD/LLD (GCP-specific risks) before any implementation begins.

Gate Responsibility

Security Gate — blocks implementation if any of the following:

  • IAM roles are over-permissive (not least-privilege)
  • Secrets, credentials, or API keys appear in code, config, or skill references
  • GCP-specific risks unaddressed: public storage buckets, default service accounts in use, unauthenticated Cloud Run endpoints without intent
  • Well-Architected Framework security pillar not addressed in the HLD
  • Cross-vendor security boundaries undefined (if multi-cloud)

Review Checklist

IAM

  • Custom roles or predefined roles scoped to minimum required permissions
  • No default compute service account used for application workloads
  • Workload Identity used for GKE pods (not SA key files)
  • Service account keys absent from code or repos
  • IAM conditions applied where scope can be narrowed further

Secrets & Credentials

  • No secrets in environment variables committed to source control
  • Secret Manager used for all sensitive config
  • No hardcoded credentials in Terraform, scripts, or skills
  • SA key files referenced by path only — values never recorded

Network

  • VPC firewall rules deny-by-default; only necessary ingress/egress open
  • Private Google Access enabled where public internet not required
  • Cloud Armor configured for public-facing endpoints
  • No 0.0.0.0/0 ingress rules without documented justification

Storage & Data

  • Cloud Storage buckets not publicly accessible unless explicitly intended
  • Uniform bucket-level access enforced
  • CMEK (Customer-Managed Encryption Keys) evaluated for sensitive data
  • BigQuery datasets not publicly shared

GCP-Specific Risks

  • No legacy metadata server access from untrusted workloads
  • OS Login enabled for GCE instances
  • Container images scanned (Artifact Registry vulnerability scanning)
  • Cloud Run services — auth required unless public by design

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 66 lines · 134 tokens per session scan A 71a5fbea3aab

Subscribe to this mod's changes

gcp-security is a skill published in the GitHub repository jpantsjoha/googlecloud-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 134 tokens to every session and 809 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

ak-cloud-deploy

Deploy an Agent Kernel project to AWS, Azure, or GCP using Terraform modules, or to any Kubernetes cluster (on-prem, baremetal, EKS) using the official Helm chart. Supports serverless and containerized modes for all three clouds. AWS supports execution modes (restsync, restasync, async, stream), queue-based scalable…

yaalalabs/agent-kernel · 146 tokens

serving-llms-vllm

Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

ariffazil/AAA · 27 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

oh-my-opencode-slim

Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.

alvinunreal/oh-my-opencode-slim · 61 tokens

reflect

Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.

alvinunreal/oh-my-opencode-slim · 53 tokens

artifact-deploy

One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".

kirodotdev/KiroCrew · 74 tokens