Skip to content
Development
Command

/scan

Launch a comprehensive security audit on the current project. Detects vulnerabilities, scans dependencies, checks OWASP Top 10, and generates a structured report.

From plugin
fusengine-agents
2233 skills43 agents33 commands
Install
$ npx -y skills add fusengine/agents --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/scan

Context preview

What this command does when you run it.

Launch a comprehensive security audit on the current project. Detects vulnerabilities, scans dependencies, checks OWASP Top 10, and generates a structured report.

Command definition

scan.md
description: Launch a comprehensive security audit on the current project. Detects vulnerabilities, scans dependencies, checks OWASP Top 10, and generates a structured report.
argument-hint: "[--full] [--deps-only] [--headers] [--auth] [path]"
disable-model-invocation: false

Security Scan

Execute a comprehensive security audit following the 5-phase workflow.

Usage

  • `/scan` - Full security audit of current project
  • `/scan --deps-only` - Dependency audit only
  • `/scan --headers` - Security headers check only
  • `/scan --auth` - Authentication patterns audit only
  • `/scan path/to/dir` - Scan specific directory

Workflow

Phase 1: DETECT

Identify project language and framework automatically:

  • Scan for marker files (package.json, composer.json, etc.)
  • Detect framework versions and dependencies
  • Map to appropriate scan patterns

Phase 2: RESEARCH

Query recent CVEs for the detected stack:

  • Use Exa to search NVD, OSV.dev, GitHub Advisory
  • Focus on dependencies found in project
  • Check for known exploits

Phase 3: SCAN

Run vulnerability patterns and dependency audit:

  • Execute language-specific grep patterns (OWASP Top 10)
  • Run `bun ${CLAUDE_PLUGIN_ROOT}/../node_modules/@fusengine/harness/dist/cli/bin.mjs scan <dir>` for automated pattern matching
  • Execute dependency audit CLI (npm audit, composer audit, etc.)
  • Detect hardcoded secrets and credentials

Phase 4: REPORT

Generate structured vulnerability report:

  • Categorize by severity: CRITICAL, HIGH, MEDIUM, LOW
  • Map findings to OWASP A01-A10 categories
  • Include file:line references and fix instructions

Phase 5: FIX

Delegate corrections to sniper agent:

  • Generate fix instructions per vulnerability
  • Invoke sniper with precise file:line + description
  • Validate all fixes applied correctly

Arguments

  • `$ARGUMENTS` specifies scan options and target path

Examples

  • `/scan` → Full OWASP + dependency + secrets audit
  • `/scan --deps-only` → Quick dependency vulnerability check
  • `/scan --auth` → JWT/OAuth/session security patterns
  • `/scan src/api/` → Scan only API directory
Read more
Ships withfusengine-agents

A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.

Get the whole plugin, auto-invoked
Stats
22
Stars
1
Views
3
Forks
Active
Maintenance
CSS
Language
MIT
License
4d ago
Last commit
7mo ago
Created

Repo: fusengine/agents