tinyworld-lowpoly-world-prompt
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists primarily of natural language instructions and prompting principles for generating 3D world data. It does not include any executable code, scripts, or external dependencies.
- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The instructions are focused on guiding the model's creative output to match a specific technical schema (JSON).
- [SAFE]: While the skill mentions command-line operations (e.g.,
npm run stats:random-island), these are documented as part of the project's statistical and aesthetic testing workflow. There are no attempts to execute these commands automatically or silently via dynamic context injection.
Audit Metadata