Claude red
Skill goharabbas321/zeoel-framework/.agents/skills/zeoel/skills/claude-red
Offensive security and penetration testing skill. Covers automated vulnerability scanning, secure-coding bypass detection, sanitization reviews, and exploit drafting.From its SKILL.md
npx -y skills add goharabbas321/zeoel-framework --skill claude-redAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 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
1.6 KB, 297 tokens by cl100k_base, as published. Nobody here has run it
/claude-red — Offensive Security & Penetration Testing
Claude-Red equips agents with offensive cybersecurity capabilities to perform penetration testing, threat modeling, and red teaming audits on SaaS architectures.
🛠️ Security Audit Protocols
1. OWASP Top 10 Auditing
- Injection Protection: Audit database interaction patterns for raw SQL concats. Enforce strict parameterization.
- Broken Authentication: Verify token expiries, session revocation logic, and CSRF token propagation.
- Sensitive Data Exposure: Check transit encryption (
HTTPS), password hashing (bcrypt/argon2), and PII encryption.
2. Penetration Testing Checklist
- Run automated vulnerability mapping on codebase boundaries.
- Attempt secure-coding logic bypasses to detect authorization flaws (e.g., IDOR in controllers).
- Verify sanitization libraries (e.g., DOMPurify for HTML, htmlspecialchars for blade).
3. Exploitation Threat Modeling
- Write attack trees demonstrating how a compromised microservice can escalate privileges.
- Document exact CVSS scores for discovered vulnerabilities.
- Provide step-by-step remediation plans.
🚫 Safe Play Guidelines
- Never: Develop weaponized exploits for remote targets.
- Never: Store unencrypted API keys or production database credentials in codebase logs.
- Always: Perform vulnerability checks against mock controllers or isolated staging stubs.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.