The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands within the project environment, specifically pnpm install, pnpm lint, pnpm typecheck, and grep. These are standard tools for managing dependencies, enforcing style rules, and searching code during development.
[EXTERNAL_DOWNLOADS]: The skill uses pnpm install to download Node.js packages from the public registry. It also references official documentation and resources from the bitrix24.com and bitrix24.github.io domains, which belong to the skill's author.
[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes untrusted user data to generate code and execute commands.
Ingestion points: User-provided inputs for page names, navigation labels, and feature specifications (referenced in references/recipes/add-page.md).
Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to prevent the agent from executing instructions embedded within the user data.
Capability inventory: The skill has the capability to write to the file system (creating pages and components) and execute shell commands (linting and dependency management) across all referenced recipes.
Sanitization: Absent. The skill does not provide mechanisms for validating or escaping user-provided strings before they are incorporated into generated files or command arguments.

b24-dashboard-template