security-threat-model

Provide the repository path and any known context such as deployment model and internet exposure, then ask for a threat model. The Skill maps components, trust boundaries, and entry points from repo evidence, confirms assumptions with you, and writes a Markdown threat model file.

It includes a system model with a Mermaid diagram, an asset table, attacker capabilities and non-capabilities, entry points with evidence anchors, 5-10 abuse paths, a prioritized threat table, and focus paths for manual security review.

Trigger it only when you explicitly want threat enumeration, abuse paths, or AppSec threat modeling of a codebase or path. It is not intended for general architecture summaries, code review, or non-security design work.

Each threat receives qualitative likelihood and impact ratings with short justifications, combined into a critical, high, medium, or low priority adjusted for existing controls. The Skill states which assumptions most influence the ranking.

Yes, it summarizes key assumptions and asks 1-3 targeted questions about deployment, exposure, and data sensitivity, then waits for your response. If you cannot answer, it proceeds with explicit assumptions and marks conditional conclusions.