The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and templates. No executable scripts, network operations, or external dependencies were found.
[NO_CODE]: Analysis confirmed the absence of any executable code files (e.g., .py, .js, .sh), which eliminates risks associated with malicious script execution or persistence.
[INDIRECT_PROMPT_INJECTION]: While the skill instructions involve reading external repository files (specifications), this represents a data ingestion surface that is considered safe because the skill does not define or utilize any tools or executable code to facilitate an attack.

sdd-specification