The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests external data from api-contracts and user-selected visual directions from ui-ux-research. This creates an attack surface where instructions embedded in these external sources could influence the agent's behavior during the project creation process.
Ingestion points: Data is read from api-contracts, ui-ux-research, and project documentation files.
Boundary markers: The skill does not define specific delimiters to isolate external data from its core instructions.
Capability inventory: The skill has the ability to execute shell commands (via pnpm and shadcn CLI) and perform broad file system write operations.
Sanitization: There is no mention of sanitizing or escaping content from external contracts before it is used in the scaffolding process.
[COMMAND_EXECUTION]: The skill requires the execution of several CLI tools and package managers to initialize the project and generate code.
Evidence: The instructions specify using pnpm, shadcn init, and @tanstack/router-cli commands.

react-vite