agentmods.dev

cloud

cloud is a skill for Claude Code, Codex from MingyiSecLab/Mingyi-Atlas. It costs 32 tokens per session (389 once invoked), scanned A, a copy of cloud-overview, Apache-2.0.

A set of security testing playbooks for cloud environments such as Amazon Web Services (AWS) and Kubernetes. It covers identity permissions, storage buckets, container access, infrastructure-as-code state files, and cloud metadata services.

In plain words
What is it for?
Use it during an authorized assessment to review AWS permissions, test exposed storage, examine Kubernetes roles, inspect Terraform state files, and follow server-side request forgery (SSRF) paths to cloud credentials.
Why use it?
It helps identify cloud access paths that can turn a small weakness into broader control of accounts, workloads, or data.

Skill for Claude CodeCodex

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

not rated 11repo 2mo ago A scan 32 tokens copy · 89% Apache-2.0

Good fit Use it during an authorized assessment to review AWS permissions, test exposed storage, examine Kubernetes roles, inspect Terraform state files, and follow server-side request forgery (SSRF) paths to cloud credentials.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/cloud
View source ↗ MingyiSecLab/Mingyi-Atlas
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
Clone the repo
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/cloud.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/cloud)
Your own site
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/cloud"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/cloud.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 389 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 89% copy Near-identical to another mod 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 $0.00032 $0.00389
Opus 5 $0.00016 $0.00195
Sonnet 5 $0.00006 $0.00078
Haiku 4.5 $0.00003 $0.00039

Measured 8d ago against content hash 9f7ecbbce1aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cloud 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 8d 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.

Origin

This is a copy

89% identical to cloud-overview — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/skills/standard/cloud/SKILL.md · 30 lines

What it actually says

Cloud Hunter Skill Catalog

Playbooks

Skill Use for
/skills/standard/cloud/aws-iam-enum/SKILL.md IAM enumeration + privesc
/skills/standard/cloud/s3-takeover/SKILL.md Dangling bucket / subdomain takeover
/skills/standard/cloud/k8s-pivot/SKILL.md Pod escape, RBAC abuse, hostPath
/skills/standard/cloud/terraform-state-leak/SKILL.md Exposed state file exploitation
/skills/standard/cloud/imds-pivot/SKILL.md SSRF → metadata → IAM role

Workflow (authenticated engagement)

  1. bash("aws sts get-caller-identity")
  2. bash("aws iam list-attached-user-policies --user-name <me>")
  3. For each attached policy: fetch JSON and iam_policy_audit
  4. Feed Terraform state via bash("aws s3 cp s3://bucket/terraform.tfstate -") → tfstate_audit
  5. bash("kubectl get pods -A -o json") → k8s_audit
  6. Every privesc primitive → kg_add_node + chain edges

Workflow (post-SSRF)

  1. metadata_endpoints("aws") for the target cloud
  2. Pivot URL one at a time via the SSRF vector
  3. Confirmed creds → credential node + leaks edge from the SSRF vuln
  4. plan_attack_chains(promote=True) to see the full path
Files

What ships with it

13 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. 8d ago First seen · 30 lines · 32 tokens per session scan A 9f7ecbbce1aa

Subscribe to this mod's changes

cloud is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 389 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to cloud-overview, differing in 12 lines, and is treated as a copy.

CloudDevOps and cloudSecurityai-agentsai-hackingai-pentestingai-securitycybersecuritydevsecops
Related

Other skills, from other repositories

cis-aws-foundations-6.5

Ensure the default security group of every VPC restricts all traffic.

CyberStrikeus/CyberStrike · 23 tokens

cis-aws-foundations-2.1.3

Ensure Organizations management account is not used for workloads.

CyberStrikeus/CyberStrike · 21 tokens

cis-aws-foundations-2.2

Maintain current AWS account contact details.

CyberStrikeus/CyberStrike · 16 tokens

cis-aws-foundations-4.4

Ensure that server access logging is enabled on the CloudTrail S3 bucket.

CyberStrikeus/CyberStrike · 24 tokens

cis-aws-foundations-6.1.2

Ensure CIFS access is restricted to trusted networks to prevent unauthorized access.

CyberStrikeus/CyberStrike · 25 tokens

cis-aws-foundations-2.4

Ensure no 'root' user account access key exists.

CyberStrikeus/CyberStrike · 20 tokens