Comprehensive red teaming methodology for both cybersecurity (MITRE ATT&CK, pentesting) and AI/LLM systems (prompt injection, jailbreaking, OWASP Top 10 LLM). Includes threat modeling, attack simulation, compliance validation (NIST, EU AI Act), and progressive attack technique references.
Add the marketplace (inside Claude Code):
/plugin marketplace add rfxlamia/skillkitInstall the plugin:
/plugin install red-teamingIntegration with OpenAI Codex CLI for complex code generation and debugging