godot-llm-integration
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation, reference patterns, and validation rules for Godot development. No malicious patterns, prompt injections, or unauthorized exfiltration attempts were detected.
- [COMMAND_EXECUTION]: The reference files include documentation for system commands (such as
sudo apt installandcargo build) to assist users with manual setup of Linux dependencies and building the NobodyWho library from source. These are presented as educational solutions for specific platform errors and are not executed automatically. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process Godot project files (
.gd,.tscn). While this constitutes an ingestion surface for untrusted data, the skill includes specific validation patterns to detect errors and does not expose dangerous capabilities that could be triggered by malicious input in these files.
Audit Metadata