All skills
jeffallan avatar

/security-reviewer

@efebc44
by jeffallanjeffallan/claude-skills12k stars
1,124

Identifies security vulnerabilities, generates structured audit reports with severity ratings, and provides actionable remediation guidance. Use when conducting security audits, reviewing code for vulnerabilities, or analyzing infrastructure security. Invoke for SAST scans, penetration testing, DevSecOps practices, cloud security reviews, dependency audits, secrets scanning, or compliance checks. Produces vulnerability reports, prioritized recommendations, and compliance checklists.

Use this Skill: https://skilld.dev/gh/jeffallan/claude-skills/security-reviewer

This session only. Nothing lands on disk.

referencessast-tools.md

≈603 tokens on demand. Your agent reads this file only when SKILL.md points to it.

SAST Tools

JavaScript/TypeScript

# Dependency vulnerabilities
npm audit
npm audit --json > npm-audit.json

# ESLint security plugin
npm install eslint-plugin-security --save-dev
npx eslint --ext .js,.ts . --plugin security

# Snyk
npx snyk test
npx snyk code test

Python

# Bandit - Python SAST
pip install bandit
bandit -r . -f json -o bandit-report.json
bandit -r . -ll  # Only high severity

# Safety - Dependency check
pip install safety
safety check
safety check -r requirements.txt --json > safety-report.json

# Pyup Safety
pip install pyupio-safety
pyupio-safety check

Go

# GoSec - Go security checker
go install github.com/securego/gosec/v2/cmd/gosec@latest
gosec ./...
gosec -fmt=json -out=gosec-report.json ./...

# Go vulnerability database
go install golang.org/x/vuln/cmd/govulncheck@latest
govulncheck ./...

Multi-Language Tools

# Semgrep - Universal SAST
pip install semgrep
semgrep --config=auto .
semgrep --config=p/security-audit .
semgrep --config=p/owasp-top-ten .

# Trivy - Comprehensive scanner
brew install trivy
trivy fs .
trivy fs --security-checks vuln,secret,config .

# SonarQube (requires server)
sonar-scanner -Dsonar.projectKey=myproject

CI/CD Integration

GitHub Actions

- name: Run Semgrep
  uses: returntocorp/semgrep-action@v1
  with:
    config: p/security-audit

- name: Run npm audit
  run: npm audit --audit-level=high

- name: Run Trivy
  uses: aquasecurity/trivy-action@master
  with:
    scan-type: 'fs'
    severity: 'CRITICAL,HIGH'

GitLab CI

security-scan:
  image: returntocorp/semgrep
  script:
    - semgrep --config=auto --json -o semgrep.json .
  artifacts:
    reports:
      sast: semgrep.json

Quick Reference

Language Primary Tool Dependency Check
JavaScript ESLint + security npm audit
TypeScript ESLint + security npm audit
Python Bandit Safety
Go GoSec govulncheck
Java SpotBugs OWASP Dependency-Check
Ruby Brakeman bundler-audit
Tool Strengths Best For
Semgrep Multi-language, custom rules General SAST
Trivy Container + code + secrets Comprehensive
Bandit Python-specific Python projects
GoSec Go-specific Go projects
npm audit Built-in, fast Node.js deps

Source: SKILL.md on GitHub

2 alerts16d5 checks · Risk CRITICAL
  • Gen Agent Trust Hub16d

    This skill provides a comprehensive framework for security auditing and penetration testing. It includes instructions for identifying vulnerabilities, scanning for secrets, and evaluating privilege escalation paths. While it contains commands for sensitive actions such as credential harvesting and local enumeration, these are documented within a professional audit context requiring explicit authorization and rules of engagement.

  • Socket16d

    1 alert: gptAnomaly

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer6mo

    5/7 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at efebc44. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Steadyupdated 5 months ago
What it can do
Reads files Runs commands
All 4 allowed tools
ReadGrepGlobBash
Other metadata
metadata
{
  "author": "https://github.com/Jeffallan",
  "version": "1.1.1",
  "domain": "security",
  "triggers": "security review, vulnerability scan, SAST, security audit, penetration test, code audit, security analysis, infrastructure security, DevSecOps, cloud security, compliance audit",
  "role": "specialist",
  "scope": "review",
  "output-format": "report",
  "related-skills": "secure-code-guardian, code-reviewer, devops-engineer, cloud-architect, kubernetes-specialist, api-designer, mcp-developer"
}
  • Security
  • DevOps
  • vulnerability-scanning
  • sast
  • code-audit
  • penetration-testing
  • secrets-scanning
  • compliance
  • infrastructure-security
  • cvss

README badge

README badge for jeffallan/claude-skills/security-reviewer

Identifies code, infrastructure, and dependency vulnerabilities through SAST scanning, manual review, and penetration testing, then produces severity-rated audit reports with remediation guidance. Covers secrets scanning, cloud security, compliance checks, and DevSecOps workflows using tools like Semgrep, Bandit, Gitleaks, and Trivy.

Generated from the current SKILL.md.

Does this skill perform active penetration testing or only static analysis?
It does both. The skill includes SAST scanning (semgrep, bandit), dependency audits, and secrets scanning, but also supports active penetration testing and reconnaissance. However, it requires written authorization and scope confirmation before any active testing.
What automated scanning tools does this skill use?
The skill runs semgrep, bandit, gitleaks, npm audit, and trivy. It treats automated tools as a starting point and requires manual review of auth, input handling, and crypto, since tools miss context-dependent vulnerabilities.
Does this skill generate compliance reports for SOC2 or ISO27001?
The skill produces structured vulnerability reports with severity ratings, findings with remediation guidance, and checklists. It references CIS benchmarks, SOC2, and ISO27001 in its knowledge base, but is designed primarily for vulnerability identification and audit support rather than compliance certification.
Can I use this skill to test production systems?
No. The skill explicitly requires written authorization and scope confirmation before active testing, and prohibits testing on production systems without explicit permission or causing service disruption or data loss.

Generated from the current SKILL.md. These answers refresh after source changes.