The Agent Skills Directory

Structured Security Analysis: The skill implements a systematic approach to threat modeling by identifying assets, trust boundaries, and attacker-controlled inputs. This is a standard and safe security practice.
Controlled Data Resolution: It resolves artifact paths using internal references like ../../references/scan-artifacts.md and ../../references/security-guidance.md, ensuring that it operates within the scope of the local repository and provided guidance.
Scope Integrity: The instructions include explicit safeguards to prevent the threat model from being influenced by specific PR diffs or local developer tooling, focusing instead on primary product and runtime surfaces.
Authoritative Source Handling: The workflow prioritizes authoritative security guidance and preserves its body unchanged, which maintains the integrity of established security policies.
No External Operations: The skill does not perform network operations, execute remote code, or download external dependencies. All logic is contained within the structured workflow for generating documentation.

threat-model