muapi-interior-design-visualizer

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the muapi CLI tool to perform image generation and editing tasks, which involves executing shell-level commands.
  • [EXTERNAL_DOWNLOADS]: The skill instructions include a fallback to curl for interacting with the api.muapi.ai endpoint, involving network operations to an external domain to transmit data and authentication headers.
  • [PROMPT_INJECTION]: There is a potential for indirect prompt injection or command injection due to the direct interpolation of user inputs into command strings.
  • Ingestion points: User-provided inputs room_type and design_style are ingested and used to construct command-line arguments.
  • Boundary markers: None identified; user inputs are inserted directly into the prompt strings for the CLI tool.
  • Capability inventory: The executing agent is granted the capability to run shell commands (muapi, curl) and access environment variables (MUAPI_API_KEY).
  • Sanitization: The skill lacks instructions for validating or sanitizing user inputs, which could allow malicious users to supply shell metacharacters or escape characters to manipulate the execution flow.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:05 PM
Security Audit — agent-trust-hub — muapi-interior-design-visualizer