Claroty Risk Triage logo

Claroty Risk Triage

Community
automateyournetwork
claroty-risk-triage

Triage Claroty xDome alerts and vulnerabilities, compute blast radius, correlate with NVD CVE data, and drive ITSM-gated workflow actions (acknowledge, label, assign, set relevance).

Overview

Publisherautomateyournetwork
Repositorynetclaw
Skill nameclaroty-risk-triage
Stars
680
Forks
189
Bundled files
Instructions only
LicenseApache-2.0
Links
  • 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 automateyournetwork on GitHub. Read the source before you install it.

Installation

Install the Claroty Risk Triage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/claroty-risk-triage
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/automateyournetwork/netclaw.git /tmp/netclaw
mkdir -p .claude/skills
cp -r /tmp/netclaw/workspace/skills/claroty-risk-triage .claude/skills/claroty-risk-triage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Claroty Risk Triage 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 Claroty Risk Triage 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 Claroty Risk Triage 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.

Claroty Risk Triage

Unified alert + vulnerability triage for OT / IoT / IoMT environments via Claroty xDome. Alerts and vulnerabilities are bundled into one skill because real incident response crosses the boundary constantly — operators investigate an alert, pivot to the affected device's CVE list, and back to the alert label.

When to Use

  • Triaging Claroty xDome alerts by severity, site, or assignee
  • Computing the blast radius of an alert (which devices, which protocols)
  • Inspecting vulnerability findings, filtering by CVSS, and listing affected devices
  • Marking a CVE as not-relevant for a specific device (mitigation in place, compensating control, patched out-of-band)
  • Acknowledging, labelling, or assigning alerts during a hunt
  • Handing off to ise-incident-response for endpoint quarantine or to servicenow-change-workflow for a remediation CR

MCP Server

  • Server: claroty-mcp
  • Command: python3 -u mcp-servers/claroty-mcp/claroty_mcp_server.py (stdio transport)
  • Auth: Bearer token via CLAROTY_API_TOKEN
  • ITSM: Write operations require a CHG\d+ CR; bypassed in NETCLAW_LAB_MODE=true

Available Tools

ToolParametersWhat It Does
list_alertsseverity?, status?, site_id?, assignee?, limit?, offset?, max_items?List security alerts with filters
get_alert_with_devicesalert_id, device_limit?Alert + affected devices in one call
list_vulnerabilitiesseverity?, cvss_min?, cve_contains?, limit?, offset?, max_items?List CVE-aligned findings
get_vulnerable_devicesvulnerability_id, limit?, offset?Devices affected by one CVE (blast radius)
acknowledge_alertalert_id, resolution, cr_number, note?Write (ITSM-gated) — set resolution state
set_vulnerability_relevancedevice_id, vulnerability_id, relevant, cr_number, note?Write (ITSM-gated) — suppress / re-enable CVE on a device
label_alertsalert_ids, labels, cr_number, replace?Write (ITSM-gated) — apply / replace labels
assign_alertsalert_ids, assignee, cr_number, note?Write (ITSM-gated) — assign alerts to a user / queue

Compose with:

  • nvd_get_cve from the nvd-cve skill for full CVSS vector decomposition
  • ise-incident-response skill for endpoint quarantine
  • servicenow-change-workflow skill to open a remediation CR if the alert demands a config change

Workflow Examples

Triage all high-severity open alerts

"List all open high-severity alerts at site warehouse-east"

Calls list_alerts(severity="high", status="open", site_id="warehouse-east"). Returns severity-sorted alert table.

Blast-radius investigation

"Show me alert a1b2c3 and every device it touches"

Calls get_alert_with_devices(alert_id="a1b2c3") and renders the alert metadata plus affected devices. From there, pivot to list_vulnerabilities filtered by site to understand combined risk.

CVE blast radius across the fleet

"What devices are vulnerable to CVE-2024-12345? Correlate with NVD for full context."
  1. list_vulnerabilities(cve_contains="2024-12345") → xDome finding ID.
  2. get_vulnerable_devices(vulnerability_id="<id>") → affected device list.
  3. nvd_get_cve(cve_id="CVE-2024-12345") (nvd-cve skill) → CVSS vector, references, fix availability.
  4. Optionally list_devices with cross-reference to Nautobot to confirm criticality.

Suppress a known false positive

"Mark CVE-2024-12345 as not-relevant for device 7a2c (mitigated by network ACL) under CHG0013001"

Calls set_vulnerability_relevance(device_id="7a2c...", vulnerability_id="<id>", relevant=False, cr_number="CHG0013001", note="mitigated by network ACL").

Label and assign an alert during a hunt

"Label alerts [a1, a2, a3] as 'ransomware-candidate' and assign to alice under CHG0013002"
  1. label_alerts(alert_ids=[...], labels=["ransomware-candidate"], cr_number="CHG0013002").
  2. assign_alerts(alert_ids=[...], assignee="alice", cr_number="CHG0013002").

Acknowledge after remediation

"Acknowledge alert a1b2c3 as resolved with a note pointing at CHG0013001's evidence"

Calls acknowledge_alert(alert_id="a1b2c3", resolution="resolved", cr_number="CHG0013001", note="...").

ITSM gating

Identical to other Claroty write tools: CHG\d+ format, ServiceNow "Implement" state check (skipped in lab mode). Rejected gate returns {"itsm_gate": {...}, "applied": false} and the xDome write is not made.

ISE handoff pattern

If a Claroty alert resolves to "compromised endpoint", do NOT call ISE quarantine from inside this skill. Hand off to ise-incident-response per Principle XIV (human-in-the-loop for external actions). That skill enforces the human decision point before any quarantine action.

Token scope expectations

If a write tool returns applied: false and an error object with status_code: 403, the ITSM gate passed and the body was correctly built — xDome rejected at RBAC. The token in CLAROTY_API_TOKEN lacks write scope on the relevant resource (alerts for acknowledge_alert/label_alerts/assign_alerts; vulnerabilities for set_vulnerability_relevance). Don't retry — escalate to whoever provisions xDome API tokens. The wrapper surfaces xDome's response body verbatim so you can see exactly which scope is missing.

Frequently asked questions

What does the Claroty Risk Triage AI skill do?

Triage Claroty xDome alerts and vulnerabilities, compute blast radius, correlate with NVD CVE data, and drive ITSM-gated workflow actions (acknowledge, label, assign, set relevance).

Why use Claroty Risk Triage on TypingMind?

Because you install it once and use it with any model. Claroty Risk Triage 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 Claroty Risk Triage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/claroty-risk-triage. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Claroty Risk Triage?

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 Claroty Risk Triage?

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

Is the Claroty Risk Triage AI skill free?

Yes. It is published on GitHub by automateyournetwork under the Apache-2.0 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇