The Agent Skills Directory

[SAFE]: The skill's primary function is to model software architecture and generate Structurizr DSL. All analyzed instructions and reference materials are strictly focused on architectural modeling and documentation.
[SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized command execution was found. The skill does not request or use high-privilege tools or perform network operations outside of standard documentation lookups.
[SAFE]: External links provided in the documentation (e.g., c4model.com, structurizr.com, arxiv.org, and workingsoftware.dev) are plain-text references to legitimate industry and academic resources.
[SAFE]: The skill includes a 'DISCOVER' phase that reads project files such as package.json and docker-compose.yml. While this constitutes a data ingestion surface for the agent, the skill's capabilities are limited to generating architectural artifacts (DSL/diagrams) and it lacks any dangerous execution or exfiltration tools that would make this surface exploitable.

stratum