cloud-recon

cloud-recon is a skill for Claude Code from MingyiSecLab/Mingyi-Atlas. It costs 34 tokens per session (2,300 once invoked), scanned C, original, Apache-2.0.

A collection of methods for finding and identifying cloud-hosted infrastructure, such as AWS storage, Azure blobs, GCP buckets, metadata services and content-delivery networks.

In plain words
What is it for?
Use it to identify cloud providers, locate buckets and storage, detect metadata endpoints, check identity and access settings, and trace content-delivery services back to their origins.
Why use it?
It helps reveal cloud assets that may be overlooked during a normal network review, including exposed storage and configuration mistakes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to identify cloud providers, locate buckets and storage, detect metadata endpoints, check identity and access settings, and trace content-delivery services back to their origins.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/cloud-recon
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.

Any agent
npx skills add MingyiSecLab/Mingyi-Atlas --skill cloud-recon
Clone the repo
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

Made for: Claude Code.

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-recon

README.md
[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/cloud-recon/github.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/cloud-recon)
Your own site
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/cloud-recon"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/cloud-recon/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 cloud-recon

Your own site · 80×15
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/cloud-recon"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/cloud-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,300 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
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 $0.00034 $0.02300
Opus 5 $0.00017 $0.01150
Sonnet 5 $0.00007 $0.00460
Haiku 4.5 $0.00003 $0.00230

Measured 7d ago against content hash ded1e703978c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

cloud-recon scanned grade C with 2 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 7d 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.

Cloud metadata endpointhighServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

# Internal: http://169.254.169.254/latest/meta-data/

Makes network callslowCapability

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

curl -s https://ip-ranges.amazonaws.com/ip-ranges.json | python3 -c "
src/skills/standard/recon/cloud-recon/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloud Infrastructure Reconnaissance Knowledge Base

Cloud reconnaissance identifies cloud-hosted assets, misconfigured storage, exposed services, and cloud-specific attack surfaces. Modern organizations run hybrid infrastructure — cloud recon is essential for complete attack surface mapping.

1. Cloud Provider Detection

Fingerprinting via DNS/Headers

See references/cloud-ip-ranges.md for the full CNAME → provider mapping table and response header fingerprinting. See references/cloud-naming-patterns.md for bucket/resource naming dictionaries.

# Check CNAME records for cloud indicators
dig <target> CNAME +short

# Common cloud CNAME patterns:
# AWS:       *.amazonaws.com, *.cloudfront.net, *.elasticbeanstalk.com
# Azure:     *.azurewebsites.net, *.blob.core.windows.net, *.azure-api.net
# GCP:       *.googleapis.com, *.appspot.com, *.run.app, *.cloudfunctions.net
# Cloudflare: *.cdn.cloudflare.net

# Check IP ranges (AWS)
curl -s https://ip-ranges.amazonaws.com/ip-ranges.json | python3 -c "
import sys, json, ipaddress
data = json.load(sys.stdin)
target = ipaddress.ip_address('<TARGET_IP>')
for prefix in data['prefixes']:
    if target in ipaddress.ip_network(prefix['ip_prefix']):
        print(f\"AWS Region: {prefix['region']}, Service: {prefix['service']}\")
"

Cloud Service Indicators

Indicator Provider Service
s3.amazonaws.com CNAME AWS S3 Storage
X-Amz-* headers AWS Various
X-Ms-* headers Azure Various
X-Cloud-Trace-Context header GCP Cloud Run/Functions
*.elasticbeanstalk.com CNAME AWS Elastic Beanstalk
*.azurewebsites.net CNAME Azure App Service
*.appspot.com CNAME GCP App Engine

2. AWS Enumeration

S3 Bucket Discovery

# Common naming patterns
for prefix in <target> <target>-backup <target>-dev <target>-staging \
    <target>-prod <target>-assets <target>-uploads <target>-logs \
    <target>-data <target>-media www.<target> cdn.<target>; do
    # Check if bucket exists
    code=$(curl -s -o /dev/null -w "%{http_code}" "https://$prefix.s3.amazonaws.com/")
    echo "$code $prefix.s3.amazonaws.com"
done

# Check bucket ACL (if accessible)
curl -s "https://<bucket>.s3.amazonaws.com/?acl"

# List bucket contents (if public)
curl -s "https://<bucket>.s3.amazonaws.com/?list-type=2&max-keys=20"

Read the full file on GitHub · 265 lines

Files

What ships with it

2 files 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. 7d ago First seen · 265 lines · 34 tokens per session scan E ded1e703978c

Subscribe to this mod's changes

cloud-recon is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 2,300 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.