scenario-game-assets
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows secure practices for managing game assets and interacting with external image generation models. Instructions prioritize schema validation and safe download procedures.
- [COMMAND_EXECUTION]: The skill includes a local utility script (
scripts/build_isometric_templates.py) to generate geometric templates. This script uses standard libraries and performs local image processing without network access or sensitive file operations. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle user-provided prompts for image generation. It mitigates potential issues by instructing the agent to validate model schemas and use specific, scoped parameters rather than passing raw input directly into generation tools.
- Ingestion points: User-provided image prompts and model schemas are processed by the agent.
- Boundary markers: The skill instructs the agent to use
model_schema_getto verify parameters before execution. - Capability inventory: Includes image generation calls (
model_run), file downloads (asset_download), and local script execution. - Sanitization: The skill recommends prompt engineering techniques to ensure output consistency and safety.
Audit Metadata