ai-ecommerce-expert-food-beverage-ecommerce-content

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The helper script scripts/imiva_mcp.py uses subprocess.Popen to launch the MCP server client. This is a standard implementation for bridging Python and Node.js components within the skill.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes the @infimind/ecom-content-cli package from the NPM registry using npx. This is the core functional component provided by the vendor (Infimind) for ecommerce content generation.
  • [PROMPT_INJECTION]: The skill processes external data in the form of user-supplied prompts and image paths. Ingestion points: User-provided strings and file paths passed through CLI arguments to imiva_mcp.py. Boundary markers: Example prompts include negative constraints to guide the AI's output. Capability inventory: The skill has the capability to read local image files and transmit data to the IMIVA API endpoint. Sanitization: Basic JSON structure validation is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-food-beverage-ecommerce-content