Skills
Navigate
skills/samuraigpt/generative-media-skills/muapi-giant-product-showcase/Gen Agent Trust Hub

muapi-giant-product-showcase

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill integrates user-supplied text and external image resources into prompts for image and video generation models, creating a vulnerability surface.
  • Ingestion points: person_description and product_image in SKILL.md.
  • Boundary markers: There are no delimiters or instructions to prevent the agent from following commands that might be embedded in the inputs.
  • Capability inventory: The skill calls the muapi CLI and curl for processing images and videos.
  • Sanitization: No input cleaning or validation is performed prior to interpolation.
  • [EXTERNAL_DOWNLOADS]: The skill connects to api.muapi.ai to send and receive media data.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the muapi CLI and curl utility, including handling API keys via environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 07:17 AM