ai-ecommerce-expert-white-background-product-image

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx -y @infimind/ecom-content-cli@latest to fetch the vendor's MCP client from the registry during execution.
  • [REMOTE_CODE_EXECUTION]: By downloading and running a remote package at runtime, the skill executes code that is not bundled within the local repository.
  • [COMMAND_EXECUTION]: The script scripts/imiva_mcp.py uses subprocess.Popen to launch the Node.js process and handle data flow between the agent and the external tool.
  • [PROMPT_INJECTION]: The skill accepts external image paths and user-defined prompts, creating a surface for indirect prompt injection.
  • Ingestion points: The images and prompt parameters passed to create_smart_refine_task in SKILL.md.
  • Boundary markers: The instructions include guidelines for the agent to maintain product structural integrity and brand visual consistency.
  • Capability inventory: The skill employs shell command execution and file system access to process e-commerce tasks.
  • Sanitization: Input parameters are serialized into JSON before being passed to the subprocess, which helps prevent basic shell injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:02 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-white-background-product-image