ai-ecommerce-expert-ecommerce-image-video-suite

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/imiva_mcp.py invokes the official IMIVA MCP CLI using subprocess.Popen. The execution is restricted to the hardcoded npx -y @infimind/ecom-content-cli@latest command, which is the recommended way to use the service's tools.
  • [EXTERNAL_DOWNLOADS]: The skill fetches the latest version of the official @infimind/ecom-content-cli package from the NPM registry at runtime using npx. This is a standard and expected dependency management pattern for this platform.
  • [DATA_EXFILTRATION]: Communication is directed to https://imiva.ecpro.com, the official domain for the IMIVA service. The skill correctly instructs users to manage sensitive API tokens via environment variables rather than hardcoding them in the skill body.
  • [PROMPT_INJECTION]: The skill processes user-supplied data (selling points, scenarios) to generate ecommerce content. This data is handled as structured JSON parameters for the tool call, minimizing the risk of prompt-based disruption of the agent's own logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-ecommerce-image-video-suite