A collection of rule and instruction sets for AI systems such as GitHub copilot and Cursor to perform generalized, structured, threat models based on a target set of documentation files.
ensingm2/AI-threat-modeling-rulesets
Skill Claude CodeCodex
Extracts system architecture and creates data flow documentation (Stages 1, 2, 6). Focuses on source traceability and accurate information extraction. Does NOT perform security analysis or quality validation.
ensingm2/AI-threat-modeling-rulesets
Skill Claude CodeCodex
Adversarial validation for all stages. Detects fabrications, identifies analytical flaws, challenges assumptions, makes approval decisions. Seeks problems rather than confirming quality. Does NOT complete deliverables or fix issues.
ensingm2/AI-threat-modeling-rulesets
Skill Claude CodeCodex
Security analysis using STRIDE/ATT&CK/Kill Chain frameworks (Stages 3, 4, 5, 6). Identifies threats, assesses risk, and develops mitigations. Does NOT perform documentation extraction or quality validation.