agentleFS
Sign inStart free
FmarzochiFmarzochi/EGC/skills/security/security-scan/SKILL.md

security-scan

Skill61 starsChanged 46 days agoApache-2.0View on GitHub

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.

  • Reads credentials
  • Installs packages

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 74 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After modifying .claude/settings.json, CLAUDE.md, or MCP configs

    line 14
  2. Distinctive:

    Before committing configuration changes

    line 15
  3. Distinctive:

    When onboarding to a new repository with existing Claude Code configs

    line 16
  4. Very specific:

    Run against the current project's .gemini/ directory:

    line 48
  5. Distinctive:

    Never modify manual-only suggestions

    line 88
  6. Distinctive:

    Run the adversarial three-agent pipeline for deeper analysis:

    line 92
  7. Distinctive:

    Add to your CI pipeline:

    line 120

“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Security Scan Skill

Audit your Claude Code configuration for security issues using AgentShield.

When to Activate

  • Setting up a new project with your AI coding tool
  • After modifying .claude/settings.json, CLAUDE.md, or MCP configs
  • Before committing configuration changes
  • When onboarding to a new repository with existing Claude Code configs
  • Periodic security hygiene checks

What It Scans

FileChecks
GEMINI.mdHardcoded secrets, auto-run instructions, prompt injection patterns
settings.jsonOverly permissive allow lists, missing deny lists, dangerous bypass flags
mcp.jsonRisky MCP servers, hardcoded env secrets, npx supply chain risks
hooks/Command injection via interpolation, data exfiltration, silent error suppression
agents/*.mdUnrestricted tool access, prompt injection surface, missing model specs

Prerequisites

AgentShield must be installed. Check and install if needed:

# Check if installed
npx egc-agentshield --version

# Install globally (recommended)
npm install -g egc-agentshield

# Or run directly via npx (no install needed)
npx egc-agentshield scan .

Usage

Basic Scan

Run against the current project's .gemini/ directory:

# Scan current project
npx egc-agentshield scan

# Scan a specific path
npx egc-agentshield scan --path /path/to/.gemini

# Scan with minimum severity filter
npx egc-agentshield scan --min-severity medium

Output Formats

# Terminal output (default): colored report with grade
npx egc-agentshield scan

# JSON: for CI/CD integration
npx egc-agentshield scan --format json

# Markdown: for documentation
npx egc-agentshield scan --format markdown

# HTML: self-contained dark-theme report
npx egc-agentshield scan --format html > security-report.html

Auto-Fix

Apply safe fixes automatically (only fixes marked as auto-fixable):

npx egc-agentshield scan --fix

This will:

  • Replace hardcoded secrets with environment variable references
  • Tighten wildcard permissions to scoped alternatives
  • Never modify manual-only suggestions

Opus 4.6 Deep Analysis

Run the adversarial three-agent pipeline for deeper analysis:

# Requires ANTHROPIC_API_KEY
export ANTHROPIC_API_KEY=your-key
npx egc-agentshield scan --gemini-2.5-pro --stream

This runs:

  1. Attacker (Red Team): finds attack vectors
  2. Defender (Blue Team): recommends hardening
  3. Auditor (Final Verdict): synthesizes both perspectives

Initialize Secure Config

Scaffold a new secure .gemini/ configuration from scratch:

npx egc-agentshield init

Creates:

  • settings.json with scoped permissions and deny list
  • GEMINI.md with security best practices
  • mcp.json placeholder

GitHub Action

Add to your CI pipeline:

- uses: Fmarzochi/agentshield@v1
  with:
    path: '.'
    min-severity: 'medium'
    fail-on-findings: true

Severity Levels

GradeScoreMeaning
A90-100Secure configuration
B75-89Minor issues
C60-74Needs attention
D40-59Significant risks
F0-39Critical vulnerabilities

Interpreting Results

Critical Findings (fix immediately)

  • Hardcoded API keys or tokens in config files
  • Bash(*) in the allow list (unrestricted shell access)
  • Command injection in hooks via ${file} interpolation
  • Shell-running MCP servers

High Findings (fix before production)

  • Auto-run instructions in GEMINI.md (prompt injection vector)
  • Missing deny lists in permissions
  • Agents with unnecessary Bash access

Medium Findings (recommended)

  • Silent error suppression in hooks (2>/dev/null, || true)
  • Missing PreToolUse security hooks
  • npx -y auto-install in MCP server configs

Info Findings (awareness)

  • Missing descriptions on MCP servers
  • Prohibitive instructions correctly flagged as good practice

Links

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free