The Agent Skills Directory

[PROMPT_INJECTION]: No prompt injection or behavior override patterns were detected in the instructions.
[DATA_EXFILTRATION]: The skill guides the collection of app metadata but explicitly forbids storing sensitive credentials such as API keys, passwords, or service account JSON files within the project context.
[COMMAND_EXECUTION]: The workflow utilizes predefined tools (get_project_context, save_project_context) from the app-store-connect-mcp environment for data persistence.

app-context