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.
npx skills add UnitOneAI/SecuritySkills --skill gcp-reviewgit clone --depth 1 https://github.com/UnitOneAI/SecuritySkillsWrote 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.
[](https://agentmods.dev/skills/unitoneai/securityskills/gcp-review)<a href="https://agentmods.dev/skills/unitoneai/securityskills/gcp-review"><img src="https://agentmods.dev/badge/skills/unitoneai/securityskills/gcp-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unitoneai/securityskills/gcp-review"><img src="https://agentmods.dev/badge/skills/unitoneai/securityskills/gcp-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.02600 |
| Opus 5 | $0.00042 | $0.01300 |
| Sonnet 5 | $0.00017 | $0.00520 |
| Haiku 4.5 | $0.00008 | $0.00260 |
Grade A, and why
gcp-review 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCP Security Posture Review
Overview
This skill performs a structured security assessment of Google Cloud Platform environments against the CIS Google Cloud Platform Foundation Benchmark v2.0.0. The benchmark is organized into seven sections covering identity and access management, logging and monitoring, networking, virtual machines, storage, Cloud SQL, and BigQuery. Each recommendation is evaluated by inspecting infrastructure-as-code definitions (Terraform, Deployment Manager), gcloud CLI output, or configuration files available in the repository.
The CIS GCP Foundation Benchmark v2.0.0 provides prescriptive guidance for hardening GCP projects and organizations. This skill evaluates each applicable control and produces a findings report with CIS recommendation IDs, severity ratings, and actionable remediation steps.
When to Use
If a target is provided via arguments, focus the review on: $ARGUMENTS
- Reviewing GCP infrastructure-as-code before deployment
- Assessing an existing GCP environment's security posture against CIS benchmarks
- Preparing for a CIS benchmark audit or compliance assessment
- Evaluating IAM bindings, org policies, VPC firewall rules, Cloud Audit Logs, or GCS bucket configurations
- Onboarding a new GCP project or organization into a security program
Context
The CIS Google Cloud Platform Foundation Benchmark v2.0.0 is a consensus-driven security configuration guide developed by the Center for Internet Security. It provides prescriptive guidance for configuring GCP projects and organizations to a hardened baseline. Google Cloud's Security Command Center can assess many of these controls natively, making this benchmark the standard for GCP security posture evaluation.
Prerequisites
- Access to GCP infrastructure-as-code files (Terraform
.tf, Deployment Manager.yaml/.jinja) - gcloud CLI output or configuration exports (if reviewing a live environment)
- IAM policy bindings and org policy definitions
- VPC and firewall rule definitions
- Cloud Audit Logs configuration
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.
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.
- 10d ago First seen · 239 lines · 83 tokens per session scan A 4b71c68e2f01
gcp-review is a skill published in the GitHub repository UnitOneAI/SecuritySkills (60 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 2,600 once invoked, about $0.0004 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.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.2
Maintain current AWS account contact details.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.