The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to perform HTTP requests against the RPGJS Studio API. This is the primary mechanism for CRUD operations on game assets, database records, and project settings.
[DATA_EXFILTRATION]: The skill reads an API key from the environment variable RPGSTUDIO_API_KEY. It contains explicit instructions to never print, log, or echo this key. While the BASE_URL can be configured via user input or a local file (RPGSTUDIO.md), which is a common pattern for API clients, the skill instructions prioritize the safety of the authentication token.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external API endpoints and a local project context file (RPGSTUDIO.md). This represents a standard attack surface where malicious data could potentially influence agent behavior, though the skill focuses on structured data processing (JSON).
[PERSISTENCE]: The skill maintains project-specific context (like the BASE_URL) in a local file named RPGSTUDIO.md. This is a legitimate use of local storage for session persistence and does not involve system-level persistence mechanisms.

rpgjs-studio