performing-gcp-security-assessment-with-forseti

performing-gcp-security-assessment-with-forseti is a skill for Claude Code, Codex from xalgorix/xalgorix. It costs 55 tokens per session (2,991 once invoked), scanned A, original, Apache-2.0.

A guide to assessing Google Cloud environments with Forseti Security, Security Command Center, and the gcloud command-line tool. It audits identity permissions, firewalls, storage access, and alignment with the CIS GCP Foundations Benchmark, a common security checklist.

In plain words
What is it for?
Use it for periodic GCP audits, new-project baselines, CIS compliance checks, multi-project reviews, and ongoing infrastructure monitoring.
Why use it?
It helps reveal risky settings across organisations and projects, including permissions inherited from higher levels. It also points out when limited visibility can make an environment look safer than it is.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is open ./scoutsuite-gcp-report/gcp-report.html.

Good fit Use it for periodic GCP audits, new-project baselines, CIS compliance checks, multi-project reviews, and ongoing infrastructure monitoring.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/xalgorix/xalgorix
agentmods
npx agentmods add skills/xalgorix/xalgorix/performing-gcp-security-assessment-with-forseti

Made for: Claude Code, Codex.

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 performing-gcp-security-assessment-with-forseti

README.md
[![agentmods](https://agentmods.dev/badge/skills/xalgorix/xalgorix/performing-gcp-security-assessment-with-forseti/github.svg)](https://agentmods.dev/skills/xalgorix/xalgorix/performing-gcp-security-assessment-with-forseti)
Your own site
<a href="https://agentmods.dev/skills/xalgorix/xalgorix/performing-gcp-security-assessment-with-forseti"><img src="https://agentmods.dev/badge/skills/xalgorix/xalgorix/performing-gcp-security-assessment-with-forseti/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.

agentmods 80×15 button for performing-gcp-security-assessment-with-forseti

Your own site · 80×15
<a href="https://agentmods.dev/skills/xalgorix/xalgorix/performing-gcp-security-assessment-with-forseti"><img src="https://agentmods.dev/badge/skills/xalgorix/xalgorix/performing-gcp-security-assessment-with-forseti.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,991 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00055 $0.02991
Opus 5 $0.00028 $0.01496
Sonnet 5 $0.00011 $0.00598
Haiku 4.5 $0.00006 $0.00299

Measured 9d ago against content hash b7d4c8a2b135, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

performing-gcp-security-assessment-with-forseti scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**How to confirm a hit (avoid false negatives):** for a suspected public bucket, actually `gsutil ls`/`curl` it anonymously; for an over-broad binding use `gcloud asset analyze-iam-policy` to prove the member can reach t
internal/tools/skills/data/cloud-security/performing-gcp-security-assessment-with-forseti/SKILL.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performing GCP Security Assessment with Forseti

When to Use

  • When conducting periodic security assessments of GCP organizations and projects
  • When onboarding new GCP projects and establishing security baselines
  • When compliance mandates CIS GCP Foundations Benchmark evaluation
  • When auditing IAM bindings, firewall rules, and storage ACLs across multiple GCP projects
  • When building continuous security monitoring for GCP infrastructure

Do not use as a replacement for GCP Security Command Center Premium for real-time threat detection, for application-level vulnerability scanning (use Web Security Scanner), or for GKE-specific security (use GKE Security Posture).

Most Often Missed & How to Confirm

  • IAM inheritance is the #1 miss: bindings flow org → folder → project, so auditing only project policies misses org/folder-level roles/owner and allUsers grants. Use gcloud asset search-all-iam-policies --scope=organizations/ORG_ID, not per-project get-iam-policy.
  • Partial results look clean: search-all-iam-policies only returns what your caller can see. Without roles/cloudasset.viewer at org scope it returns a subset, not an error - verify your scope coverage before trusting "no findings."
  • Empty SCC ≠ secure: findings only exist for enabled detectors. Confirm Security Health Analytics / Event Threat Detection are enabled (gcloud scc settings services) before treating an empty result as a pass.
  • Conditional bindings and deny policies: a binding can look permissive but be gated by bindings[].condition, or shadowed by an org deny policy - inspect both, don't read the role alone.
  • Default service accounts (*[email protected], AppEngine) often retain roles/editor and rarely surface as "users" - check them explicitly.
  • Storage: legacy ACLs grant access even when IAM looks clean. Check gsutil iam get AND gsutil acl get, plus uniform bucket-level access status.

How to confirm a hit (avoid false negatives): for a suspected public bucket, actually gsutil ls/curl it anonymously; for an over-broad binding use gcloud asset analyze-iam-policy to prove the member can reach the resource. Don't conclude negative until: org + folder + project IAM are all audited, SCC detectors are confirmed enabled, default SAs are checked, and both ACLs and IAM are evaluated for storage.

Read the full file on GitHub · 306 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. 9d ago First seen · 306 lines · 55 tokens per session scan A b7d4c8a2b135

Subscribe to this mod's changes

performing-gcp-security-assessment-with-forseti is a skill published in the GitHub repository xalgorix/xalgorix (975 stars, last pushed 2d ago), licensed Apache-2.0. It adds 55 tokens to every session and 2,991 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories