The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions intended to guide an AI agent in visual design refinement. No executable scripts, binaries, or configuration files capable of system modification were detected.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify design contexts or codebases provided by the user. While this creates a surface for indirect prompt injection where instructions could be embedded in the analyzed code, the skill itself provides no mechanisms for data exfiltration or arbitrary command execution, mitigating the risk.
[SAFE]: The external links provided in the metadata and README are for provenance and attribution purposes, pointing to a well-known public repository on GitHub. No remote code execution or automated downloads are attempted.

quieter