Scan code for security vulnerabilities, identifying potential attack vectors and providing remediation guidance.
/plugin marketplace add marcel-Ngan/ai-dev-team/plugin install marcel-ngan-ai-dev-team@marcel-Ngan/ai-dev-teamThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Scan code for security vulnerabilities, identifying potential attack vectors and providing remediation guidance.
| Category | ID | Description | Detection Method |
|---|---|---|---|
| Injection | A03 | SQL, NoSQL, OS, LDAP injection | Pattern matching, taint analysis |
| Broken Auth | A07 | Authentication/session flaws | Flow analysis |
| Sensitive Data | A02 | Exposure of sensitive data | Data flow tracking |
| XXE | A05 | XML external entity attacks | Parser configuration check |
| Access Control | A01 | Authorization failures | Access pattern analysis |
| Misconfig | A05 | Security misconfiguration | Config analysis |
| XSS | A03 | Cross-site scripting | Output encoding check |
| Deserialization | A08 | Insecure deserialization | Type checking |
| Components | A06 | Vulnerable dependencies | Version checking |
| Logging | A09 | Insufficient logging | Audit coverage |
## Static Security Scan
### Code Patterns Checked
1. **Input Validation**
- Unvalidated user input
- Missing sanitization
- Type coercion issues
2. **Authentication**
- Hardcoded credentials
- Weak password handling
- Session management flaws
3. **Authorization**
- Missing access checks
- Privilege escalation paths
- IDOR vulnerabilities
4. **Data Handling**
- Sensitive data in logs
- Unencrypted storage
- Insecure transmission
## Dependency Vulnerability Check
### Package Analysis
- Known CVEs in dependencies
- Outdated packages with fixes
- Abandoned/unmaintained packages
- License compliance issues
## Configuration Security
### Areas Checked
- Default credentials
- Debug mode settings
- CORS configuration
- Security headers
- TLS/SSL settings
- Cookie attributes
## Security Vulnerability Report
**Scan Date:** {{date}}
**Target:** {{target}}
**Scan Type:** {{type}}
**Tool Version:** {{version}}
### Executive Summary
- **Total Vulnerabilities:** {{total}}
- **Critical:** {{critical}}
- **High:** {{high}}
- **Medium:** {{medium}}
- **Low:** {{low}}
---
### Critical Vulnerabilities
#### VULN-001: {{title}}
**Severity:** Critical
**CWE:** CWE-{{number}}
**CVSS:** {{score}}
**Location:**
- File: `{{file}}`
- Line: {{line}}
**Description:**
{{description}}
**Vulnerable Code:**
```{{language}}
{{code_snippet}}
Proof of Concept: {{poc_description}}
Remediation: {{fix_description}}
Fixed Code:
{{fixed_code}}
References:
...
...
...
| Priority | Vulnerability | Effort | Owner | Target Date |
|---|---|---|---|---|
| 1 | VULN-001 | 2h | TBD | Immediate |
| 2 | VULN-002 | 4h | TBD | This sprint |
| ... |
---
## Language-Specific Checks
### JavaScript/TypeScript
| Vulnerability | Pattern | Example |
|--------------|---------|---------|
| Prototype pollution | `obj[userInput]` | `target[key] = value` |
| eval injection | `eval(userInput)` | `eval(code)` |
| DOM XSS | `innerHTML = userInput` | `el.innerHTML = data` |
| Path traversal | Path without validation | `fs.readFile(userPath)` |
### Python
| Vulnerability | Pattern | Example |
|--------------|---------|---------|
| Command injection | `os.system(userInput)` | `os.system(cmd)` |
| SQL injection | f-string in query | `f"SELECT * WHERE id={id}"` |
| Pickle RCE | Unpickling user data | `pickle.loads(data)` |
| YAML load | Unsafe YAML load | `yaml.load(data)` |
### Java
| Vulnerability | Pattern | Example |
|--------------|---------|---------|
| SQL injection | String concat in query | `"SELECT * WHERE id=" + id` |
| XXE | Default XML parser | `DocumentBuilder.parse(input)` |
| Deserialization | ObjectInputStream | `ois.readObject()` |
| Path traversal | File with user path | `new File(userPath)` |
---
## Integration Points
### CI/CD Integration
```yaml
# GitHub Actions example
security-scan:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Security Scan
run: |
# Invoke vulnerability scan skill
# Fail on critical/high findings
continue-on-error: false
#!/bin/bash
# Run security scan on staged files
STAGED_FILES=$(git diff --cached --name-only)
# Scan staged files for vulnerabilities
# Block commit if critical issues found
security-secret-scan - Credential detectionsecurity-compliance-check - Standards compliancesecurity-dependency-audit - Dependency vulnerabilitiesanalysis-code - General code analysisjira-comment-logging or confluence-technical-docsThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.