Wazuh Cloud Container

Organization

gensecaihq

wazuh-cloud-container

Interpret Wazuh cloud and container alerts — AWS (CloudTrail, GuardDuty, VPC Flow, Security Hub), Azure, GCP, Microsoft Graph, Office 365, GitHub and Docker — with their key fields, normal baselines and pivots; use for any alert from a cloud or container integration.

Overview

Publisher	gensecaihq
Repository	`Wazuh-Autopilot`
Skill name	`wazuh-cloud-container`
Stars	61
Forks	15
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by gensecaihq on GitHub. Read the source before you install it.

Installation

Install the Wazuh Cloud Container AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/gensecaihq/Wazuh-Autopilot/tree/main/backend/app/skills/wazuh-cloud-container
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/gensecaihq/Wazuh-Autopilot/tree/main/backend/app/skills/wazuh-cloud-container

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/gensecaihq/Wazuh-Autopilot.git /tmp/Wazuh-Autopilot
mkdir -p .claude/skills
cp -r /tmp/Wazuh-Autopilot/backend/app/skills/wazuh-cloud-container .claude/skills/wazuh-cloud-container

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wazuh Cloud Container in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wazuh Cloud Container on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wazuh Cloud Container is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Wazuh Cloud and Container

Cloud and SaaS logs reach Wazuh through integration modules on the manager (or a collector agent), so the agent is usually the manager or collector — the real actor is in data.*. Always pivot on the identity, source IP and resource from data, not on agent.name.

Integrations in the stock ruleset

Source	Groups	Key rules (level)	Key fields
AWS CloudTrail	`amazon`, `aws`, `aws_cloudtrail`	rule 80202 (level 3, API call), rule 80203 (level 4, API call with error), rule 80253 (level 3, console login success), rule 80254 (level 5, console login failed), rule 80255 (level 10, possible break-in attempt), rule 80252 (level 10, high number of deleted objects)	`data.aws.eventName`, `eventSource`, `userIdentity.arn`, `sourceIPAddress`, `awsRegion`, `errorCode`
AWS GuardDuty	`aws_guardduty`	rules 80301, 80302, 80303 (levels 3, 6, 10 by finding severity); with remote IP: rules 80305, 80306, 80307	`data.aws.title`, `service.action.actionType`, `severity`, resource
AWS VPC Flow / WAF / Config / Inspector / Macie / KMS / Security Hub	`aws_vpcflow`, `aws_waf`, `aws_config`, `aws_inspector`, `aws_macie`, `aws_kms`, `aws_security_hub`	By group	Service-specific under `data.aws.*`
Azure	`azure`	rule 87802 (level 3, "Azure: AD $(activityDisplayName)"), rule 87811 (level 3, Log Analytics operation)	`data.activityDisplayName`, operation, caller
Microsoft Graph (Defender/Entra alerts & incidents)	`ms-graph`	rule 99503 (level 6, alert/incident not resolved and not a false positive)	alert title, severity, entities
GCP	`gcp`	rule 65053 (level 3, firewall rule created), rule 65054 (level 3, firewall rule deleted), rule 65056 (level 3, logging bucket deleted), rule 65057 (level 3, logging sink deleted), rule 65070 (level 3, new service account created)	`data.gcp.protoPayload.*`, principal, resource
Office 365	`office365`	rule 91556 (level 12, phishing/malware events from Exchange Online Protection / Defender), rule 91700 (level 14, malware detected in file), rule 91724 (level 10, suspicious download activity by user)	`data.office365.UserId`, `Operation`, `ClientIP`, `Workload`
GitHub	`github`	rule 91152 (level 9, environment actions secret removed), rule 91197 (level 7, organization actions secret created); secret-scanning groups `git_secret_scanning`, `git_repository_secret_scanning`	`data.github.actor`, `action`, `repo`, `org`
Docker (docker-listener)	`docker`	rule 87907 (level 3, command launched in container), rule 87908 (level 5, shell session started in container), rule 87910 (level 3, file copied from host into container), rule 87902 (level 5, container destroyed)	`data.docker.Actor.Attributes.name`, `image`, `Action`

Kubernetes audit logs are not covered by the stock ruleset (only EKS controls via Security Hub). Monitoring kube-apiserver audit events needs a custom decoder and custom rules (example to create: custom rule 100500 for pods/exec by a non-admin identity). Say so rather than implying coverage.

Many cloud rules are level 3 by design — the stock ruleset records activity and leaves importance to context. A level-3 DeleteTrail, StopLogging, logging-sink deletion or root-account login matters far more than its level.

What "normal" looks like (baseline before judging)

Identities: known automation roles and CI users make most API calls at steady rates; humans log in from known IP ranges and regions.
Use get_alerts_aggregated and search_security_events with the identity or IP as query over 7d to establish prevalence before calling an action anomalous.

High-signal patterns

Pattern	Where	ATT&CK
Logging disabled/deleted (CloudTrail `StopLogging`/`DeleteTrail`, GCP sink/bucket deletion)	CloudTrail, GCP	T1562.008
Console login failures then success, new region/IP, no MFA	CloudTrail, Entra/Graph, O365	T1110, T1078.004
New access keys / service accounts / role trust changes	CloudTrail, GCP	T1098.001, T1136.003
Mass object deletion (rule 80252) or bucket policy made public	CloudTrail	T1485, T1530
Mailbox forwarding rules, suspicious downloads (rule 91724)	Office 365	T1114.003, T1530
Secrets removed/rotated unexpectedly, secret-scanning hits	GitHub	T1552
Shell in container (rule 87908), host file copied in (rule 87910), privileged container	Docker	T1609, T1611

Containment is outside Wazuh active response

Wazuh AR acts on endpoints with agents; it cannot disable an IAM user, revoke a cloud session or delete a GitHub token. Record cloud containment as manual recommendations in the finding (disable access key, revoke sessions, restore logging, rotate secret) with the exact identity and resource. Only host-level actions for a compromised VM or container host with a Wazuh agent go to response-planner.

Output

add_entities: cloud identity (type user, value = ARN / UPN / principal), source IP, resource names (type host or url as appropriate), repository.
link_mitre for the pattern (cloud sub-techniques where they apply).
add_finding: source integration, identity, what happened, baseline comparison, verdict, and manual cloud containment steps.

Frequently asked questions

What does the Wazuh Cloud Container AI skill do?

Why use Wazuh Cloud Container on TypingMind?

Because you install it once and use it with any model. Wazuh Cloud Container is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wazuh Cloud Container in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gensecaihq/Wazuh-Autopilot/tree/main/backend/app/skills/wazuh-cloud-container. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Wazuh Cloud Container?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wazuh Cloud Container?

As many as you like. As long as a model supports skills, you can use Wazuh Cloud Container with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wazuh Cloud Container AI skill free?

Yes. It is published on GitHub by gensecaihq under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Serving Llms Vllm

NousResearch

OrganizationPopular

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Modal

Serverless GPU cloud for ML jobs and model APIs.

Huggingface Hub

HuggingFace hf CLI: search/download/upload models, datasets.

Pinecone

Managed vector DB for production RAG and search.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Wazuh Cloud and Container

Integrations in the stock ruleset

What "normal" looks like (baseline before judging)

High-signal patterns

Containment is outside Wazuh active response

Output

Frequently asked questions

Related AI Skills

Set up your own AI workspace now