ai-ecommerce-expert-reference-image-video

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill uses npx to download and execute the @infimind/ecom-content-cli package. This is the official tool provided by the vendor (Beijing Infimind Technology / 极睿科技) for the IMIVA platform, representing a legitimate dependency.
  • [DYNAMIC_EXECUTION]: The scripts/imiva_mcp.py script uses subprocess.Popen to launch the MCP server. The command string is constructed from static constants rather than dynamic user input, which prevents command injection risks.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill documentation correctly advises users to manage their API tokens via environment variables (MCP_TOKEN) instead of hardcoding them, ensuring sensitive credentials are not exposed in code or history.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts and reference materials to generate video content. It includes instructions for fact-checking and boundary markers to ensure accuracy, which mitigates risks associated with untrusted data ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:02 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-reference-image-video