The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use common shell utilities such as grep, find, and ripgrep to analyze project structure and verify architectural compliance. These operations are performed locally and are restricted to the project directory.
[DYNAMIC_EXECUTION]: The skill includes a local utility script, scripts/validate-vite-architecture-skill.mjs, which is used to validate the skill's own file structure and content consistency. Analysis of the script confirms it performs safe, read-only file system checks without network access or unsafe evaluation functions.
[INDIRECT_PROMPT_INJECTION]: By its nature of auditing external project source code, the skill has an attack surface for indirect prompt injection. However, the skill provides specific instructions and validation checklists that serve as boundaries to mitigate the risk of following instructions embedded within the audited code.

vite-architecture