The Agent Skills Directory

[SAFE]: The skill is designed for static code analysis and architectural advice. It uses the Read, Grep, and Glob tools to inspect existing source code. These tools are inherently low-risk as they do not permit file modification or arbitrary command execution.
[SAFE]: No signs of prompt injection, data exfiltration, or obfuscation were found across the skill files. The instructions focus strictly on software engineering best practices using established industry methodologies (Fowler, Ruby Science).
[SAFE]: While the skill analyzes untrusted user code (a potential surface for Indirect Prompt Injection), its lack of write or execution capabilities mitigates this risk. The agent serves as an advisor, and any output is provided as text for the user to review.

ruby-refactoring