ai-ecommerce-expert-nano-banana-pro-ecommerce-image

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and run the official @infimind/ecom-content-cli package from the NPM registry at runtime. This is the intended delivery method for the platform's tools.
  • [COMMAND_EXECUTION]: The helper script scripts/imiva_mcp.py executes the npx command using subprocess.Popen. It uses an argument list format which avoids shell-based command injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions and image paths. This is a necessary part of the e-commerce generation workflow and is documented as a standard capability. 1. Ingestion points: prompt and images arguments in scripts/imiva_mcp.py. 2. Boundary markers: None explicitly implemented in code, but instructions for product fact verification are provided in SKILL.md. 3. Capability inventory: Subprocess execution of the platform CLI tools. 4. Sanitization: Arguments are validated as valid JSON structures 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-nano-banana-pro-ecommerce-image