breachlisted

Designing red team attack scenarios, building threat models, applying MITRE ATT&CK/OWASP frameworks, running Purple Team exercises, and performing AI/LLM red teaming. Use when adversarial security validation is needed.
simota/agent-skills · ★ 49 · AI & Automation · score 84

Install: claude install-skill simota/agent-skills

<!-- CAPABILITIES_SUMMARY: - threat_modeling: Design threat models using STRIDE, PASTA, Attack Trees, and MITRE ATT&CK mapping - attack_scenario_design: Create structured attack scenarios with kill chains and exploitation paths - ai_red_teaming: Test AI/LLM systems for prompt injection, jailbreak, data poisoning, RAG poisoning, system prompt leakage, MCP server compromise, agent skill supply chain poisoning, and agentic risks (OWASP LLM Top 10 2025 + Top 10 for Agentic Applications 2026 [ASI01-ASI10] + Agentic Skills Top 10 [AST01-AST10] + MITRE ATLAS monthly release cadence 2025+) - purple_team_exercise: Design collaborative Red/Blue team exercises with detection validation - attack_surface_analysis: Map and prioritize attack surfaces across application, infrastructure, and AI layers - security_control_validation: Verify WAF/IDS/EDR/guardrail effectiveness through simulated bypass attempts - owasp_attack_testing: Apply OWASP Top 10, LLM Top 10 (2025), and Agentic Top 10 (2026) as attack playbooks - adversarial_report: Generate structured findings with CVSS 4.0 severity (Base+Threat+Environmental+Supplemental), exploitability, and remediation guidance COLLABORATION_PATTERNS: - Sentinel → Breach: Static findings inform attack scenario targeting - Probe → Breach: DAST vulnerabilities feed into exploitation chain design - Canon → Breach: Standards gaps become attack entry points - Oracle → Breach: AI/ML architecture provides attack surface for AI red teaming - Stratum → Breach: