Vulnerability Scanner logo

Vulnerability Scanner

Community
Firstp1ck
vulnerability-scanner

Agents should invoke this skill when checking CVEs or known vulnerabilities in installed packages, dependencies, Docker images, OS packages, exposed services, or software versions. Produces severity-rated scan reports.

Overview

PublisherFirstp1ck
Repositorypi-coding-agent-forge
Skill namevulnerability-scanner
Stars
93
Forks
22
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 Firstp1ck on GitHub. Read the source before you install it.

Installation

Install the Vulnerability Scanner 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/Firstp1ck/pi-coding-agent-forge/tree/main/pi-skill-vulnerability-scanner/skills/vulnerability-scanner
  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/Firstp1ck/pi-coding-agent-forge.git /tmp/pi-coding-agent-forge
mkdir -p .claude/skills
cp -r /tmp/pi-coding-agent-forge/pi-skill-vulnerability-scanner/skills/vulnerability-scanner .claude/skills/vulnerability-scanner
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vulnerability Scanner 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 Scanner 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 Scanner 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 Scanner

CVE research, system package auditing, and container image vulnerability scanning. Uses web search for CVE lookups and local tools for package/image analysis.

Quick Start

Quick CVE Check for a Specific Software

  1. Identify the software and version
  2. Web search: "[software name] [version] CVE site:nvd.nist.gov OR site:github.com/advisories"
  3. Assess: Is the target version affected?
  4. Report: Severity, affected versions, fix version, remediation steps

CVE Web Search Workflow

Step 1: Identify Software Versions

Gather current versions of monitored software:

bash
# Docker
docker --version
docker compose version

# System packages (Arch Linux)
pacman -Q <package-name>

# Pi-hole (via SSH or API)
# Check ../workspace-devops/MEMORY.md for known version

# Gitea (via web UI or API)
curl -s http://<gitea-host>:3000/api/v1/version

Step 2: Search for CVEs

Use web search with targeted queries:

SoftwareSearch Query
Pi-hole"Pi-hole" CVE 2025 2026 vulnerability
Gitea"Gitea" CVE 2025 2026 security advisory
Docker"Docker Engine" CVE 29.2 vulnerability
Ollama"Ollama" CVE vulnerability security
OpenClaw"OpenClaw" CVE vulnerability security

Useful sources:

  • NVD: site:nvd.nist.gov
  • GitHub Advisories: site:github.com/advisories
  • MITRE: site:cve.mitre.org
  • Vendor security pages (e.g., blog.gitea.com/security)

Step 3: Assess Impact

For each CVE found:

FieldDescription
CVE IDe.g., CVE-2026-XXXXX
CVSS Score0.0 - 10.0
SeverityCritical / High / Medium / Low
Affected versionsWhich versions are vulnerable
Target versionWhat is running
ExploitabilityIs there a public exploit?
ImpactWhat can an attacker do?
Fix versionWhich version patches this?
MitigationWorkaround if upgrade isn't immediate

Step 4: Report

Update MEMORY.md:

  • Add to Known Vulnerabilities table if affected
  • Update CVE Watch List with last check date
  • Log in Audit History

System Package Audit (Arch Linux)

Using arch-audit

bash
# Install if not present
sudo pacman -S arch-audit

# Check for vulnerable packages
arch-audit

# Show only critical/high
arch-audit --upgradable

# JSON output for parsing
arch-audit --format json

Manual Package Check

bash
# List all installed packages with versions
pacman -Q

# Check for orphaned packages (potential attack surface)
pacman -Qdt

# Check for packages not in official repos
pacman -Qm

# Check for outdated packages
checkupdates

Evaluate Findings

SeverityAction
Critical CVE with public exploitUpdate immediately: sudo pacman -Syu
High CVE, no public exploitPlan update within 24h
Medium CVEInclude in next maintenance window
Low CVEDocument, update when convenient

Docker Image Scanning

Using Trivy (Recommended)

bash
# Install trivy
sudo pacman -S trivy  # Arch
# or
docker run --rm aquasec/trivy image <image-name>

# Scan a specific image
trivy image <image-name>:<tag>

# Scan with severity filter
trivy image --severity CRITICAL,HIGH <image-name>:<tag>

# Scan all running container images
docker ps --format '{{.Image}}' | sort -u | while read img; do
    echo "=== Scanning: $img ==="
    trivy image --severity CRITICAL,HIGH "$img"
done

# JSON output
trivy image --format json --output scan-results.json <image-name>

Using Grype (Alternative)

bash
# Install grype
curl -sSfL https://raw.githubusercontent.com/anchore/grype/main/install.sh | sh -s -- -b /usr/local/bin

# Scan an image
grype <image-name>:<tag>

# Only critical and high
grype <image-name>:<tag> --only-fixed --fail-on critical

Evaluate Image Findings

For each vulnerable image:

  1. Check if the vulnerability is in a dependency we actually use
  2. Check if a fixed version of the base image exists
  3. If fixable: update the image and redeploy
  4. If not fixable: assess risk and document as accepted risk

Scan Report Format

When delivering vulnerability scan results:

markdown
# Vulnerability Scan Report

**Date:** YYYY-MM-DD
**Scope:** [What was scanned]
**Scanner:** [web search / arch-audit / trivy / grype]

## Summary

| Severity | Count |
|---|---|
| Critical | X |
| High | X |
| Medium | X |
| Low | X |

## Critical Findings

### CVE-YYYY-XXXXX: [Brief Description]

- **Severity:** Critical (CVSS 9.8)
- **Affected:** [software] [version]
- **Our version:** [version]
- **Status:** Vulnerable / Not affected / Patched
- **Fix:** Upgrade to [version]
- **Reference:** [NVD link]

## Recommendations

1. [Prioritized list of actions]

## Next Scan

Scheduled: [date or trigger condition]

CVE Watch List Management

Maintain the watch list in MEMORY.md:

  1. Add new software when it's deployed to the infrastructure
  2. Update versions when software is upgraded
  3. Record check dates after each CVE lookup
  4. Remove software when it's decommissioned

Recommended Check Frequency

SoftwareFrequencyReason
Internet-facing servicesWeeklyHighest exposure
LAN services (Gitea, Pi-hole)Bi-weeklyLower exposure but valuable targets
Docker EngineMonthlyCore infrastructure
System packagesMonthlyarch-audit covers this
Development dependenciesPer-releasecargo audit, npm audit

Zero skill — Vulnerability scanning and CVE monitoring

Frequently asked questions

What does the Vulnerability Scanner AI skill do?

Agents should invoke this skill when checking CVEs or known vulnerabilities in installed packages, dependencies, Docker images, OS packages, exposed services, or software versions. Produces severity-rated scan reports.

Why use Vulnerability Scanner on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Firstp1ck/pi-coding-agent-forge/tree/main/pi-skill-vulnerability-scanner/skills/vulnerability-scanner. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vulnerability Scanner?

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 Scanner?

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

Is the Vulnerability Scanner AI skill free?

Yes. It is published on GitHub by Firstp1ck 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 👇