The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell commands including mkdir, cat, and test to organize architecture directories and write DSL workspace files.
[COMMAND_EXECUTION]: The skill executes the structurizr CLI tool for workspace validation (structurizr validate) and generating static site exports (structurizr export).
[PROMPT_INJECTION]: The skill templates user-provided values like system names and personas into DSL files, creating a surface for indirect prompt injection.
Ingestion points: User-defined system names, personas, and container descriptions in Standard Tasks 1 and 3.
Boundary markers: The skill utilizes quoted heredocs (<<'DSL'), which is a security best practice that prevents shell expansion of the injected content.
Capability inventory: The skill possesses file-writing capabilities and the ability to execute the structurizr CLI.
Sanitization: While no explicit string sanitization is mentioned, the use of quoted heredocs and the specific Structurizr DSL schema provide significant structural constraints.
[SAFE]: All external references provided in the skill point to the official docs.structurizr.com documentation domain.

structurizr-architecture