The Agent Skills Directory

[SAFE]: The skill functions as a technical auditor for Godot projects, utilizing a structured protocol to evaluate code and scene integrity based on engine best practices.
[COMMAND_EXECUTION]: The provided diagnostic scripts, such as audit_signals.py and purge_report_generator.gd, perform local static analysis and performance monitoring. These tools use standard file I/O and Godot's Performance/ObjectDB APIs to generate reports without executing arbitrary shell commands or accessing sensitive system areas.
[DATA_EXFILTRATION]: No network operations or data exfiltration patterns were detected. The skill reads local project data for auditing purposes only and does not communicate with external servers.
[REMOTE_CODE_EXECUTION]: The skill does not download external code or scripts. All auditing logic is contained within the local file structure.
[PROMPT_INJECTION]: The persona-driven instructions are focused on technical enforcement and architectural purity. No patterns were found that attempt to bypass AI safety guidelines or override system prompts.
[CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or access to sensitive configuration paths (e.g., .env, .ssh, .aws) were identified.

godot-auditor