muapi-interior-design-visualizer
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided values for 'room_type' and 'design_style' by inserting them into image generation prompts. This represents a standard surface for indirect prompt injection common in generative AI skills. \n
- Ingestion points: Input variables in SKILL.md. \n
- Boundary markers: Absent. \n
- Capability inventory: Shell command execution (muapi CLI) and network requests (curl). \n
- Sanitization: Absent. \n- [COMMAND_EXECUTION]: The skill utilizes 'muapi' CLI commands and 'curl' for its core functionality. These are standard operations for its intended purpose. \n- [EXTERNAL_DOWNLOADS]: The skill communicates with 'api.muapi.ai' to perform image generation and polling, which is expected behavior for an API-driven visualizer.
Audit Metadata