ai-ecommerce-expert-viral-sales-video

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses npx -y @infimind/ecom-content-cli@latest to dynamically download and execute the official IMIVA Ecommerce MCP tool. This is the intended operation for accessing the service's features.
  • [DYNAMIC_EXECUTION]: The scripts/imiva_mcp.py file uses subprocess.Popen to launch the MCP CLI. The command is constructed using a fixed package name and parameters passed via standard input, minimizing injection risks.
  • [DATA_EXPOSURE]: The skill provides instructions for managing authentication tokens via environment variables (MCP_TOKEN), which is a secure practice compared to hardcoding credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied assets such as referenceVideo and productImages. * Ingestion points: Local file paths or HTTPS URLs provided as arguments to the tool. * Boundary markers: The skill instructions lack explicit delimiters for external content, but the data is passed to a structured API. * Capability inventory: Subprocess execution is limited to the official vendor CLI. * Sanitization: Parameters are serialized to JSON before being passed to the tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-viral-sales-video