Config Security Scan

/config-security-scan [path]

- API keys, tokens, passwords in CLAUDE.md
- Hardcoded credentials in hook scripts
- Secrets in MCP server configs
- Bearer tokens in agent definitions
- .env files committed to git

- dangerouslySkipPermissions in settings.json
- Overly broad tool permissions (all tools for simple agents)
- MCP servers with filesystem write access
- Hooks with shell execution and no validation
- Agents with Bash tool that don't need it

- Unknown/untrusted MCP servers
- MCP servers with network access + filesystem access
- Missing authentication on MCP endpoints
- MCP servers running as root/admin
- Unverified npm packages in MCP configs

- Hooks that execute user input
- Hooks without error handling
- Hooks that modify git config
- Hooks that access external networks
- Hooks with hardcoded paths

- Agents with unnecessary tools
- Agents with system-level Bash access
- Agent descriptions that could enable prompt injection
- Agents without clear scope boundaries

- Unused MCP server configs
- Deprecated settings
- Conflicting rules
- Missing recommended security settings

# Step 1: Find all config files
find .claude/ -type f \( -name "*.json" -o -name "*.md" -o -name "*.yml" -o -name "*.yaml" -o -name "*.js" -o -name "*.mjs" -o -name "*.ts" \)

# Step 2: Secret patterns
grep -rn "api[_-]?key\|password\|secret\|token\|bearer\|sk-\|pk_\|ghp_\|gho_\|xoxb-\|xoxp-" .claude/

# Step 3: Permission checks
grep -rn "dangerouslySkipPermissions\|allowedTools.*Bash\|shell_exec\|eval(" .claude/

# Step 4: MCP config review
cat .mcp.json 2>/dev/null | jq '.mcpServers | keys'

# Step 5: Hook review
ls .claude/hooks/ 2>/dev/null

# Config Security Scan Report
Scanned: [path]
Date: [timestamp]

## Summary
- CRITICAL: X issues
- HIGH: Y issues
- MEDIUM: Z issues
- LOW: W issues

## CRITICAL Issues

### [Issue Title]
**File:** [path]
**Line:** [number]
**Issue:** [description]
**Fix:** [remediation]

## Recommendations
1. [Action item]