cloud-security

cloud-security is a skill for Claude Code, Codex from rajitsaha/100xprism. It costs 56 tokens per session (3,643 once invoked), scanned A, original, MIT.

A security and privacy audit for cloud deployments, including Google Cloud infrastructure, application programming interfaces, containers, and personal-data handling. It also checks concerns related to GDPR and CCPA, privacy laws.

In plain words
What is it for?
Use it to inspect deployed cloud configuration and report or fix security and privacy issues; it is not a review of code changes.
Why use it?
It helps uncover risky access settings, exposed data, weak API protections, container problems, and missing compliance controls.

Skill for Claude CodeCodex

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/rajitsaha/100xprism/cloud-security
Any agent
npx skills add rajitsaha/100xprism --skill cloud-security
Clone the repo
git clone --depth 1 https://github.com/rajitsaha/100xprism

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 cloud-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/rajitsaha/100xprism/cloud-security.svg)](https://agentmods.dev/skills/rajitsaha/100xprism/cloud-security)
Your own site
<a href="https://agentmods.dev/skills/rajitsaha/100xprism/cloud-security"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/cloud-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,643 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 $0.00056 $0.03643
Opus 5 $0.00028 $0.01821
Sonnet 5 $0.00011 $0.00729
Haiku 4.5 $0.00006 $0.00364

Measured 4d ago against content hash f98cbf3e32c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloud-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 4d 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.

.agents/skills/cloud-security/SKILL.md · 239 lines

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.

Cloud Security — Cloud Security & Data Privacy Scan

Covers GCP infrastructure hardening, data privacy (PII/GDPR/CCPA), API security, container security, and compliance.

Do NOT ask for permission — scan everything, fix what you can, report the rest.


Step 0 — Detect cloud config

PROJECT_ROOT=$(git rev-parse --show-toplevel)
INSTRUCTION_FILE=$(for f in CLAUDE.md AGENTS.md .cursorrules; do [ -f "$PROJECT_ROOT/$f" ] && echo "$PROJECT_ROOT/$f" && break; done)
GCP_PROJECTS=$(grep -rh "GCP_PROJECT\|GOOGLE_CLOUD_PROJECT\|gcloud.*--project" ${INSTRUCTION_FILE:-/dev/null} .env.example terraform/ 2>/dev/null | grep -oE '[a-z][a-z0-9-]{4,28}' | sort -u | grep -v "^--" || true)
HAS_DOCKER=$(ls Dockerfile docker-compose.yml 2>/dev/null | head -1 || true)
HAS_TERRAFORM=$(ls terraform/*.tf infra/*.tf 2>/dev/null | head -1 || true)

Section 1 — GCP IAM & Access Control

For each GCP project detected:

for PROJECT in $GCP_PROJECTS; do
  echo "=== IAM: $PROJECT ==="
  gcloud projects get-iam-policy "$PROJECT" --format=json 2>/dev/null \
    | python3 -c "
import sys,json
p=json.load(sys.stdin)
bad=['roles/editor','roles/owner','roles/iam.securityAdmin','roles/storage.admin']
[print('[HIGH]',b['role'],m) for b in p.get('bindings',[]) for m in b['members'] if b['role'] in bad and ('serviceAccount' in m or 'allUsers' in m)]"
  gcloud iam service-accounts list --project="$PROJECT" --format="value(email)" 2>/dev/null \
    | while read SA; do
        n=$(gcloud iam service-accounts keys list --iam-account="$SA" --filter="keyType=USER_MANAGED" --format="value(KEY_ID)" 2>/dev/null | wc -l)
        [ "$n" -gt 0 ] && echo "[HIGH] $SA: $n user-managed key(s) — use Workload Identity instead"
      done
  gcloud projects get-iam-policy "$PROJECT" --format=json 2>/dev/null | grep -E "allUsers|allAuthenticatedUsers" && echo "[CRITICAL] Public IAM binding found" || true
done

Section 2 — GCP Network & Firewall

for PROJECT in $GCP_PROJECTS; do
  echo "=== Network: $PROJECT ==="
  gcloud compute firewall-rules list --project="$PROJECT" --format=json 2>/dev/null \
    | python3 -c "
import sys,json
sp={'22','3389','5432','6379','3306','27017','6443'}
[print('[CRITICAL] Firewall',r['name'],'port',p,'open to 0.0.0.0/0') for r in json.load(sys.stdin) if '0.0.0.0/0' in r.get('sourceRanges',[]) or '::/0' in r.get('sourceRanges',[]) for a in r.get('allowed',[]) for p in a.get('ports',[]) if str(p) in sp]"
  gcloud sql instances list --project="$PROJECT" --format=json 2>/dev/null \
    | python3 -c "
import sys,json
for i in json.load(sys.stdin):
  n,ip=i['name'],i.get('settings',{}).get('ipConfiguration',{})
  [print('[CRITICAL] Cloud SQL',n,'public IP open to',net['value']) if net.get('value') in ('0.0.0.0/0','::/0') else print('[MEDIUM] Cloud SQL',n,'public IP enabled') for net in ip.get('authorizedNetworks',[])] if ip.get('ipv4Enabled') else None
  print('[HIGH] Cloud SQL',n,'SSL not required') if not ip.get('requireSsl') and ip.get('sslMode','')!='ENCRYPTED_ONLY' else print('[PASS] Cloud SQL',n,'SSL enforced')
  print('[HIGH] Cloud SQL',n,'backups disabled') if not i.get('settings',{}).get('backupConfiguration',{}).get('enabled') else None"
done

Read the full file on GitHub · 239 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. 4d ago First seen · 239 lines · 56 tokens per session scan A f98cbf3e32c2

Subscribe to this mod's changes

cloud-security is a skill published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 3,643 once invoked, about $0.0003 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.