The Agent Skills Directory

[SAFE]: The skill's primary function is to discover existing project configurations and create a new project structure. All operations, including workspace scanning and file creation, are consistent with its stated purpose and intended functionality.
[COMMAND_EXECUTION]: Shell commands are used via the Bash tool to create the project's directory structure. These commands use static paths defined in the skill and do not incorporate unvalidated external input, posing no risk of command injection.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting content from various local workspace files to configure the project. This is a risk factor associated with the skill's primary aggregation purpose.
Ingestion points: Files including portfolio.json, marketing-project.json, tips-project.json, and various Markdown files in the output/communicate/customer-narrative/ directory.
Boundary markers: The skill does not currently use explicit delimiters or instructions to ignore embedded content within processed files.
Capability inventory: The skill utilizes Bash (directory creation), Write, Edit, and the ability to trigger other agents and skills via the Agent and Skill tools.
Sanitization: No explicit sanitization or validation logic for the content of processed files is described in the workflow.

website-setup