ai-ecommerce-expert-xiaohongshu-note-image-set

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/imiva_mcp.py uses subprocess.Popen to launch the MCP client. It executes the npx command to run the external tool @infimind/ecom-content-cli.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes remote code at runtime via npx -y @infimind/ecom-content-cli@latest. This package is the official client for the IMIVA platform mentioned in the skill description.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted user data which is then passed to external AI models.
  • Ingestion points: User-provided arguments for productName, sellingPoints, targetAudience, and usageScenario in the create_koc_note_package_task tool.
  • Boundary markers: None identified in the provided scripts to delimit user input from instructions.
  • Capability inventory: The skill has the ability to execute shell commands via subprocess.Popen and perform network operations through the MCP client.
  • Sanitization: No input validation or escaping is performed on the user-supplied strings before they are passed to the invoke function in scripts/imiva_mcp.py.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-xiaohongshu-note-image-set