The Agent Skills Directory

[PROMPT_INJECTION]: The skill does not contain instructions designed to override agent safety filters or bypass system prompts. All instructions are focused on game development workflows and technical implementations.
[DATA_EXPOSURE]: No hardcoded secrets, API keys, or sensitive file paths (such as .ssh or .aws) were found. The skill does not include any network operations that could be used for data exfiltration.
[OBFUSCATION]: The skill uses clear, human-readable language and code. No Base64, zero-width characters, homoglyphs, or other obfuscation techniques were detected.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote script downloads (e.g., via curl or wget) and does not suggest the installation of unverified third-party packages.
[DYNAMIC_EXECUTION]: The code samples provided are standard Unity C# and Unreal C++. There is no use of unsafe deserialization, runtime code generation, or dynamic execution functions like eval().
[PRIVILEGE_ESCALATION]: The skill does not request or use elevated privileges. All commands and scripts are scoped to standard development environments.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not utilize dynamic context injection syntax (!command) to execute shell commands at load time.

game-developer