cloud-recon

A command for searching public cloud storage and for finding the server address hidden behind Cloudflare, a service that sits in front of websites and filters traffic. It checks AWS, Azure, and Google Cloud naming patterns and DNS history.

In plain words
What is it for?
Use it during an authorized assessment to search for public cloud storage linked to a keyword or investigate whether a target's original server address is exposed.
Why use it?
It helps security testers find accidentally public buckets, files, or queues and identify exposed origin servers that may bypass Cloudflare protections. The command can also use a certificate-and-DNS fallback when one tool is unavailable.

Command

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 commands/awarexone/agentic-bug-hunter/cloud-recon
Clone the repo
git clone --depth 1 https://github.com/Awarexone/Agentic-Bug-Hunter
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 450 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 $0.00000 $0.00450
Opus 5 $0.00000 $0.00225
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 3d ago against content hash f4df97b4af48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloud-recon 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 3d 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.

commands/cloud-recon.md · 44 lines

What it actually says

/cloud-recon

Find cloud-storage misconfigurations and origin IPs that bypass CloudFlare.

Usage

/cloud-recon --keyword acme
/cloud-recon --keyword acme --s3-only
/cloud-recon --cf-bypass api.target.com

What it runs

Tool Mode What it finds
s3scanner --keyword Public/listable S3 buckets across AWS, DigitalOcean Spaces, Wasabi, Linode
cloud_enum --keyword AWS S3, Azure blobs/files/queues, GCP storage with permutation patterns
cloudfail --cf-bypass DNS-history-based CloudFlare origin IP discovery

When cloudfail is missing the script falls back to crt.sh + dig and flags any subdomain that resolves to an IP outside CloudFlare's published ranges — typical origin-IP leak symptom.

Why this matters

  • A world-readable S3 bucket holding PII or backups is usually rated High to Critical ($1k–$10k+).
  • An exposed CloudFlare origin IP lets you bypass WAF rules; combined with a Host-header trick or a vulnerability that the WAF was masking, payouts climb fast.
  • Both classes are easy to triage and nearly always in-scope.

Output

findings/cloud/<timestamp>/ with:

  • s3scanner.txt — buckets that exist + their permission bits
  • cloud_enum.txt — multi-cloud OSINT hits
  • cloudfail.txt or non_cf_ips.txt — origin-IP candidates
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. 3d ago First seen · 44 lines · 0 tokens per session scan A f4df97b4af48

Subscribe to this mod's changes

cloud-recon is a command published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,651 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 450 tokens. 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.

Related

Other commands, from other repositories

recon

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/ / directory. Usage: /recon target.com.

elementalsouls/Claude-BugHunter · 65 tokens

hunt

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt .target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome].

elementalsouls/Claude-BugHunter · 63 tokens

token-scan

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan [--chain solana].

elementalsouls/Claude-BugHunter · 79 tokens

autopilot

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].

elementalsouls/Claude-BugHunter · 49 tokens

triage

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.

elementalsouls/Claude-BugHunter · 45 tokens

validate

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.

elementalsouls/Claude-BugHunter · 41 tokens