ugc-unboxing-video

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions provide a setup command to add a Model Context Protocol (MCP) server from https://mcp.apimage.org/mcp. This connects the agent to external tools and services provided by the vendor.
  • [COMMAND_EXECUTION]: The documentation contains a shell command (claude mcp add) intended for environment configuration. This command includes a placeholder for an API key (sk_your_api_key), which is standard for tool integration.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill is designed to process external product information, photographs, and metadata via the create_brand_asset function and prompt interpolation.
  • Boundary markers: The instructions utilize clear section headers and specific prompt blocks (PROD, LOOK, BEATS) to structure data handling.
  • Capability inventory: The skill facilitates video scene generation, audio pairing, and references tools for packaging mockups and quality assurance reviews.
  • Sanitization: The guidelines strongly advise against generating packaging text and emphasize using real photographs to ensure accuracy and prevent the model from creating misleading content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 09:16 AM