Security scan

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield, then turn the findings into a prioritized remediation plan. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.From its SKILL.md

Install

npx -y skills add KuCh4u/ECC --skill security-scan

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

6.3 KB, as published. Nobody here has run it

Security Scan Skill

Audit your Claude Code configuration for security issues using AgentShield, then prioritize what to fix.

How To Run It

Delegate the scan to the security-reviewer agent as a subtask. Raw scanner output is long and single-use — keeping it in a subagent leaves only the prioritized findings in the main context.

path — defaults to the current project. Accepts a .claude/ path, a repo root, or a checked-in template directory.
--format — json for CI, markdown for handoffs, html for standalone reports.
--fix — applies only fixes AgentShield marks as safe and auto-fixable. State the planned edits before applying them.

When to Activate

Setting up a new Claude Code project
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

File	Checks
`CLAUDE.md`	Hardcoded secrets, auto-run instructions, prompt injection patterns
`settings.json`	Overly permissive allow lists, missing deny lists, dangerous bypass flags
`mcp.json`	Risky MCP servers, hardcoded env secrets, npx supply chain risks
`hooks/`	Command injection via interpolation, data exfiltration, silent error suppression
`agents/*.md`	Unrestricted tool access, prompt injection surface, missing model specs

Prerequisites

AgentShield must be installed. Check and install if needed:

# Check if installed
npx ecc-agentshield --version

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

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

Usage

Basic Scan

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

# Scan current project
npx ecc-agentshield scan

# Scan a specific path
npx ecc-agentshield scan --path /path/to/.claude

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

Output Formats

# Terminal output (default) — colored report with grade
npx ecc-agentshield scan

# JSON — for CI/CD integration
npx ecc-agentshield scan --format json

# Markdown — for documentation
npx ecc-agentshield scan --format markdown

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

Auto-Fix

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

npx ecc-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 ecc-agentshield scan --opus --stream

This runs:

Attacker (Red Team) — finds attack vectors
Defender (Blue Team) — recommends hardening
Auditor (Final Verdict) — synthesizes both perspectives

Initialize Secure Config

Scaffold a new secure .claude/ configuration from scratch:

npx ecc-agentshield init

Creates:

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

GitHub Action

Add to your CI pipeline:

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

Severity Levels

Grade	Score	Meaning
A	90-100	Secure configuration
B	75-89	Minor issues
C	60-74	Needs attention
D	40-59	Significant risks
F	0-39	Critical 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 CLAUDE.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

Triage Discipline

AgentShield output is the source of truth. Do not invent findings, and keep scanner facts separate from your own follow-up judgment.

Active runtime findings first — hardcoded secrets, broad permissions, executable hooks, MCP servers with shell/filesystem/remote transport or unpinned npx, and agent prompts that handle untrusted content without defenses.
Lower-confidence inventory separately — docs examples, template examples, plugin manifests, project-local optional settings. These are not runtime risk and mixing them in inflates the count until nobody reads the report.
For each critical or high finding, give: file path, severity, runtime confidence, why it matters, exact remediation, and whether it is safe to auto-fix.
Re-run after fixes and report the before/after score.

Output Contract

Security grade and score
Counts by severity and by runtime confidence
Critical and high findings with exact paths
Lower-confidence findings grouped separately
Remediation order
Commands run, and whether the scan was local, CI, or npx-backed