Skills
skills/samuraigpt/generative-media-skills/muapi-floor-plan-rendering/Gen Agent Trust Hub

muapi-floor-plan-rendering

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the muapi CLI and curl to orchestrate image generation and editing tasks. These operations are restricted to the intended purpose of the skill and use standard environment variables for authentication.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with api.muapi.ai to send prompts and retrieve generated architectural renderings. This network activity is documented and appropriate for the service being used.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating the user-provided floor_plan_description into prompts for the image generation model. This is a common pattern for such tools and is considered safe in this context as it only affects image output.
  • Ingestion points: floor_plan_description input in SKILL.md.
  • Boundary markers: None.
  • Capability inventory: Image generation and editing via muapi CLI and API.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:05 PM
Security Audit — agent-trust-hub — muapi-floor-plan-rendering