guitar-product-render
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing external data sources without explicit validation or boundary markers.
- Ingestion points: The skill processes project briefs and Blender scene files that may contain instructions embedded in metadata or object names (SKILL.md, references/runtime-presentation.md).
- Boundary markers: Instructions do not provide specific delimiters or warnings to ignore embedded content during processing.
- Capability inventory: The skill makes use of powerful Blender MCP operations for rendering, lighting manipulation, and scene management (SKILL.md).
- Sanitization: No input sanitization or validation steps are mentioned for external files.
- [DYNAMIC_EXECUTION]: The instructions describe a workflow involving Python-based multi-scene drivers and the handling of script execution failures, representing a surface for dynamic code execution within the Blender environment (references/studio-recipes.md).
Audit Metadata