The Agent Skills Directory

[DATA_EXPOSURE]: The skill reads local project files such as routes, components, and documentation to infer user journeys, which is consistent with its stated purpose.
[COMMAND_EXECUTION]: The instructions require the agent to create a directory and write documentation to docs/hci/user-journeys.md.
[PROMPT_INJECTION]: The skill processes project files and user-supplied arguments which could theoretically contain indirect prompt injections; however, the lack of network or high-privilege capabilities limits the risk to the content of the generated report.

journey-map