The Agent Skills Directory

[SAFE]: The skill is designed for providing architectural guidance and templates. It contains no executable code or scripts within the skill structure itself.
[PROMPT_INJECTION]: No malicious patterns attempting to override system prompts, bypass safety filters, or extract system instructions were detected. The instructional language is focused on documentation workflows.
[DATA_EXFILTRATION]: No evidence of data exfiltration was found. The skill does not access sensitive local file paths (like .ssh or .aws) and does not perform network operations beyond providing informative links to documentation tools.
[EXTERNAL_DOWNLOADS]: The skill mentions external tools such as Structurizr, Mermaid, and ArchUnit, which are well-known and standard in the software architecture domain. Instructions for installing packages like adr-tools are provided as user guidelines for their own environments, not as agent-side execution steps.
[COMMAND_EXECUTION]: The skill includes code snippets for Mermaid diagrams, Structurizr DSL, and GitHub Actions. These are provided as templates for the user to document their own projects and are not executed by the agent.
[OBFUSCATION]: No obfuscated strings, Base64-encoded commands, homoglyphs, or hidden Unicode characters were identified in any of the analyzed files.

ddd-architecture-doc