muapi-interior-design-visualizer

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-supplied strings (room_type and design_style) into prompts for image generation and editing tasks.
  • Ingestion points: Inputs defined in SKILL.md (room_type, design_style).
  • Boundary markers: Absent; user inputs are directly interpolated into the natural language prompt strings without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill executes shell commands through the muapi CLI and curl to interact with the api.muapi.ai service for image processing (SKILL.md).
  • Sanitization: There is no evidence of input validation, filtering, or escaping of the user-provided data before it is sent to the image generation models.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the muapi CLI and curl to perform room generation and furnishing operations. These commands interact with the developer's infrastructure (muapi.ai) and utilize environment variables for authentication.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 05:11 PM