The Agent Skills Directory

[SAFE]: The skill content is entirely instructional and follows established game design frameworks such as MDA and Flow Theory. No malicious intent was found in the text or instructions.
[PROMPT_INJECTION]: There are no instructions designed to override agent safety or bypass intended constraints. The skill uses role-play elements strictly for educational game design purposes.
[DATA_EXFILTRATION]: No network access patterns or sensitive file read operations (e.g., .env, .ssh) were identified. The skill does not attempt to collect or transmit user data to external domains.
[COMMAND_EXECUTION]: While the skill permits the use of the Bash tool for building prototypes, this is within the scope of user-authorized development tasks. No unauthorized or suspicious command sequences were found.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or unverified dependencies. No external URLs for binary payloads are present.

game-prototype