The Agent Skills Directory

[SAFE]: The skill and its associated reference files consist of technical documentation and code examples for game systems. No malicious patterns, instructions, or vulnerabilities were identified during analysis.
[PROMPT_INJECTION]: The skill contains no instructions intended to bypass safety guidelines, override system behavior, or extract sensitive prompt data.
[DATA_EXFILTRATION]: No network requests, hardcoded credentials, or unauthorized access to local sensitive files (e.g., .ssh, .aws, .env) are present.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts, nor does it use dynamic execution functions like eval() or exec() on untrusted input.
[COMMAND_EXECUTION]: There are no shell commands or subprocess calls that interact with the host system in a dangerous manner.

game-developer