Sponsor Suno AI Music arrow_forward
Slash Command

Security Scan

Comprehensive database security scanner with OWASP compliance checks,

Type
Slash Command
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026

What Security Scan is

Security Scan is a slash command published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Security Scan gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Security Scan

Claude Code

  1. Download security-scan.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/database/database-security-scanner/commands/security-scan.md, shared under the repository's MIT license. Read the full file on GitHub.

Implement production-grade database security scanning for PostgreSQL and MySQL that detects 50+ security vulnerabilities including weak passwords, excessive permissions, SQL injection vectors, missing encryption, exposed ports, and insecure configurations. Provides OWASP Database Security compliance reports, automated remediation scripts, and continuous security monitoring with SOC2/HIPAA/PCI DSS audit trails.

When to Use This Command

Use /security-scan when you need to:

  • Perform security audits for compliance (SOC2, HIPAA, PCI DSS)
  • Detect vulnerabilities before security incidents occur
  • Validate database hardening after deployment
  • Generate security reports for stakeholders and auditors
  • Implement continuous security scanning in CI/CD pipeline
  • Identify privilege escalation risks and over-permissioned users

DON'T use this when:

  • You lack permission to query security-sensitive system tables
  • Database is in active development (expect frequent config changes)
  • You need application-level security testing (use SAST/DAST tools)
  • Cloud-managed database with built-in security scanning (use AWS RDS/CloudSQL tools)
  • You lack remediation authority (read-only security assessment)

Design Decisions

This command implements comprehensive multi-layer security scanning because:

  • Checks 50+ OWASP Database Security vulnerabilities
  • Validates encryption at rest and in transit (SSL/TLS)
  • Detects privilege escalation and over-permissioned roles
  • Identifies SQL injection vectors in stored procedures
  • Scans for weak authentication and default credentials
  • Generates automated remediation scripts for findings

Alternative considered: Manual security checklist

  • Simple for small databases (<10 users, <50 tables)
  • Time-consuming and error-prone for large databases
  • No continuous monitoring or automation
  • Recommended for one-time assessments only

Alternative considered: Commercial security tools (Tenable, Qualys)

  • More comprehensive (network scanning, OS hardening)
  • Expensive licensing ($10k-50k/year)
  • Better for enterprise-wide security programs
  • Recommended when budget allows and compliance requires

Prerequisites

Before running this command:

  1. Database superuser or security admin permissions
  2. Access to system catalogs (pg_catalog, information_schema)
  3. Understanding of compliance requirements (PCI DSS, HIPAA, SOC2)
  4. Authority to implement remediation recommendations
  5. Backup before applying security hardening changes

Implementation Process

Step 1: Connect with Security Admin Privileges

Ensure connection has permissions to query user roles, grants, and configurations.

Step 2: Run Vulnerability Scans

Check authentication, authorization, encryption, auditing, and network security.

Step 3: Analyze Findings

Categorize vulnerabilities by severity (critical, high, medium, low).

Step 4: Generate Remediation Scripts

Create SQL scripts to fix identified issues with rollback procedures.

Step 5: Validate and Re-scan

Apply fixes in staging, validate, then re-scan to confirm remediation.

Output Format

The command generates:

  • security_report.md - Human-readable security audit report with severity ratings
  • vulnerabilities.json - Machine-readable findings for CI/CD integration
  • remediation.sql - SQL script to fix identified vulnerabilities
  • compliance_matrix.xlsx - Mapping to SOC2/HIPAA/PCI DSS controls
  • security_baseline.yml - Configuration baseline for future scans

Code Examples

Example 1: PostgreSQL Comprehensive Security Scanner

#!/usr/bin/env python3
"""
Production-ready PostgreSQL security scanner implementing OWASP
Database Security Project checks with automated remediation.
"""

import psycopg2
from psycopg2.extras import RealDictCursor
from typing import List, Dict, Optional
from dataclasses import dataclass
from enum import Enum
import json
import logging
from datetime import datetime

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
…

Error Handling

Configuration Options

Scan Scope

  • Full scan: All 50+ security checks (recommended for compliance)
  • Quick scan: Critical and high severity only (fast assessment)
  • Compliance scan: Specific to SOC2/HIPAA/PCI DSS requirements
  • Custom scan: User-defined check selection

Severity Thresholds

  • Critical: Immediate exploitation risk (exposed passwords, SQL injection)
  • High: Significant security impact (excessive permissions, no encryption)
  • Medium: Security weakness (insecure config, missing hardening)

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Security Scan?

Security Scan is a slash command for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Comprehensive database security scanner with OWASP compliance checks,

How do I install Security Scan in Claude Code?

Download security-scan.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Security Scan in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Security Scan safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.