The Agent Skills Directory

[SAFE]: The skill provides structured guidance and templates for information architecture tasks like site mapping and URL design. It does not contain any executable scripts, binary files, or commands that interact with the system or network.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to read product marketing context from files such as .agents/product-marketing.md. While reading external data is a potential surface for indirect prompt injection, the skill possesses no dangerous capabilities (e.g., shell execution, file writing, or network access) that could be leveraged for an attack. The risk is negligible as it only influences text and diagram generation.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns or package installations were detected. The skill relies entirely on built-in language model capabilities and standard markdown/Mermaid rendering.

site-architecture