produce-game-2d-map-assets
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill is designed for game asset creation and uses standard libraries for image processing.
- [COMMAND_EXECUTION]: The skill uses local Python scripts to automate asset extraction and map preview composition. These scripts operate on local files and do not execute external code or arbitrary shell commands beyond their intended functions.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect injection surface. Ingestion points: scripts/compose_layered_preview.py reads JSON placement data, and scripts/extract_prop_pack.py reads images and label strings. Boundary markers: Absent. Capability inventory: Local file I/O for images and JSON, with no network access or privilege escalation mechanisms. Sanitization: Includes path existence validation but lacks explicit content sanitization. Risk is assessed as safe given the restricted capabilities and environment.
Audit Metadata