godot-2d-gameplay
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains an inherent indirect prompt injection risk surface.
- Ingestion points: The skill instructs the agent to locate, read, and inspect external files such as
project.godot,.gd,.tscn, and.tresfiles inSKILL.md. - Boundary markers: No specific boundary definitions or delimiters are specified to isolate or disregard potential malicious instructions within the project files.
- Capability inventory: The skill defines capabilities to execute system shell commands via the Godot binary, specifically
godot --versionandgodot --headless --path . --editor --quit, as detailed inSKILL.mdandreferences/verification-and-troubleshooting.md. - Sanitization: There is no evidence of filtering or sanitization of input arguments before passing control to the command line execution environment.
Audit Metadata