muapi-product-showcase-video

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill takes user-provided text for 'ingredients_description' and 'brand_colors' and interpolates them directly into prompts for the 'bytedance-seedream-v4.5-edit' and 'seedance-v1.5-pro-i2v-fast' models.
  • Ingestion points: ingredients_description and brand_colors inputs in SKILL.md.
  • Boundary markers: None present; inputs are placed directly into the natural language prompt string.
  • Capability inventory: Executes muapi CLI tools and curl network requests to external API endpoints.
  • Sanitization: No escaping or validation of user-provided text is performed before prompt interpolation.
  • [COMMAND_EXECUTION]: The skill uses the muapi CLI to perform image editing and video generation tasks, and provides instructions for the agent to use curl for API calls if CLI aliases are missing.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the external endpoint api.muapi.ai to process generation requests and poll for results.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 07:17 AM