Vulnerability Prioritization logo

Vulnerability Prioritization

Organization
gensecaihq
vulnerability-prioritization

Prioritize Wazuh vulnerability-detector findings with CISA KEV, FIRST EPSS, CVSS and asset context into CISA SSVC decisions and remediation SLAs; use for vulnerability sweeps, CVE alerts or patch-priority questions.

Overview

Publishergensecaihq
RepositoryWazuh-Autopilot
Skill namevulnerability-prioritization
Stars
61
Forks
15
Bundled files
Instructions only
LicenseMIT
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 gensecaihq on GitHub. Read the source before you install it.

Installation

Install the Vulnerability Prioritization 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/gensecaihq/Wazuh-Autopilot/tree/main/backend/app/skills/vulnerability-prioritization
  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/gensecaihq/Wazuh-Autopilot.git /tmp/Wazuh-Autopilot
mkdir -p .claude/skills
cp -r /tmp/Wazuh-Autopilot/backend/app/skills/vulnerability-prioritization .claude/skills/vulnerability-prioritization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vulnerability Prioritization 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 Vulnerability Prioritization 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 Vulnerability Prioritization 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.

Vulnerability Prioritization

CVSS alone ranks too many things "critical". Prioritize by exploitation evidence, then likelihood, then impact in this environment. Aligns with NIST CSF 2.0 ID.RA, NIST SP 800-53r5 RA-5 / SI-2, CIS Controls v8.1 Control 7 (Continuous Vulnerability Management), and NIST SP 800-40r4 (enterprise patch management as preventive maintenance).

What Wazuh gives you

The vulnerability detector matches the syscollector package inventory against CVE feeds and raises one alert per CVE and package, with fields under data.vulnerability.*: cve, severity, cvss.cvss3.base_score (or score.base), package.name, package.version, status (Active / Solved), published, reference.

RuleLevelMeaning
rule 235035Active, severity Low
rule 235047Active, severity Medium or Untriaged
rule 2350510Active, severity High
rule 2350613Active, severity Critical
rule 235023CVE no longer affects the package (solved, e.g. after an upgrade)
rule 235073vulnerabilities cleared for the agent

So the alert level is just the vendor severity. It says nothing about exploitation or exposure, and that's what this skill adds. rules 23502 and 23507 are good remediation evidence: use them to confirm a fix instead of re-scanning. Detection lags the package scan interval, so note data freshness.

For configuration weaknesses on the same hosts (open services, weak SSH settings), load wazuh-sca-hardening. SCA failures often turn a Track item into Attend.

Data gathering

  1. get_wazuh_vulnerability_summary — counts by severity and top CVEs.
  2. get_wazuh_critical_vulnerabilities — the critical/high set with affected agents.
  3. get_wazuh_vulnerabilities(agent_id=...) — per-host detail when scoping.
  4. get_wazuh_vulnerabilities(agent_id=..., severity="critical") per host for scoping (vulnerability_assessment on the MCP server is a prompt template, not a callable tool). get_agent_ports(agent_id) shows whether the vulnerable service is actually listening. That's your Exposure input.
  5. For exploitation data use search_external_context with the CVE id only: "CVE-XXXX-YYYY CISA KEV", "CVE-XXXX-YYYY EPSS". Never send hostnames.

Decision order

  1. CISA KEV — listed in the Known Exploited Vulnerabilities catalog? Exploitation in the wild is confirmed. (KEV entries also carry a federal due date.)
  2. FIRST EPSS — probability of exploitation activity in the next 30 days (0–1) and percentile. EPSS ≥ 0.1 (or ≥ 90th percentile) is a strong signal.
  3. CVSS (v4.0 where available, else v3.1) base score, adjusted for environment: internet exposure, compensating controls, asset criticality.

SSVC decision (CISA Deployer tree, simplified)

Decision points: Exploitation (none / public PoC / active), Exposure (small / controlled / open — i.e. internet-facing), Automatable (yes/no — can an attacker reliably exploit at scale), Mission & Well-being impact (low / medium / high).

OutcomeTypical conditionsMeaning
Actactive exploitation (KEV) + open exposure or high impactremediate immediately, escalate
Attendactive exploitation with controlled exposure, or PoC + open exposure + automatableremediate sooner than standard; supervisor attention
Track*PoC or high EPSS but limited exposure/impacttrack closely; standard timeline, re-check often
Trackno known exploitation, low exposurestandard patch cycle

Remediation SLAs (org defaults — adjust to policy)

SSVCTarget
Act48 hours (or KEV due date if sooner), mitigate same day if patch unavailable
Attend7 days
Track*30 days
Tracknext regular maintenance cycle (≤ 90 days)

Mitigations when patching is not possible: disable the vulnerable service, restrict exposure (firewall / host_deny via a human-approved plan), virtual patching, increased monitoring (hand off to detection-engineer).

Output table

| CVE | Package | Hosts | KEV | EPSS (pct) | CVSS | Exposure | SSVC | SLA | Action |

Group by CVE, list affected host counts, top 25 rows. Note data freshness (last vulnerability scan time per agent).

Output

  • save_report(kind="vulnerability", title, body_md) with the table and summary for sweeps; for a spike tied to a case, add_finding titled Vulnerability priorities.
  • create_case for any Act item on an internet-facing or critical asset (severity high/critical), with CVE, hosts and recommended mitigation.
  • standard_refs: CISA-KEV, FIRST-EPSS, CISA-SSVC, NIST-800-53r5:RA-5, NIST-800-53r5:SI-2, CIS-v8.1:7.

Frequently asked questions

What does the Vulnerability Prioritization AI skill do?

Prioritize Wazuh vulnerability-detector findings with CISA KEV, FIRST EPSS, CVSS and asset context into CISA SSVC decisions and remediation SLAs; use for vulnerability sweeps, CVE alerts or patch-priority questions.

Why use Vulnerability Prioritization on TypingMind?

Because you install it once and use it with any model. Vulnerability Prioritization 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 Vulnerability Prioritization in TypingMind?

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

Which AI models can use Vulnerability Prioritization?

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 Vulnerability Prioritization?

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

Is the Vulnerability Prioritization 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

Set up your own AI workspace now

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