The Agent Skills Directory

[SAFE]: The skill operates as a static analysis framework for evaluating code quality and architectural simplicity. It does not contain any instructions for network access, file system modifications (other than refactoring suggestions), or execution of untrusted code.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided source code. This represents a potential surface for indirect prompt injection where malicious instructions could be embedded in the code under review. However, the skill's instructions are focused on structural and architectural analysis (e.g., cyclomatic complexity, layer counting) rather than executing or blindly following instructions within the analyzed data. The risk is minimized by the analytical nature of the workflow. (Severity: LOW)
[NO_CODE]: The skill consists entirely of Markdown instructions and reference guides. It does not include executable scripts (Python, JavaScript, shell) or external package dependencies, significantly reducing the attack surface.

kiss