ai-ecommerce-expert-reference-detail-page

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the @infimind/ecom-content-cli package at runtime. This is the official utility for the IMIVA platform described in the skill documentation.
  • [COMMAND_EXECUTION]: The script scripts/imiva_mcp.py uses subprocess.Popen to launch the external MCP client tool. This is a standard implementation for bridging the agent with specialized Node.js tools.
  • [PROMPT_INJECTION]: The skill ingests user-supplied product information and images, creating a surface for indirect prompt injection via the e-commerce generation workflow. 1. Ingestion points: Input parameters such as productImages and extraDescription are passed to the create_detail_page_task tool in SKILL.md. 2. Boundary markers: No specific delimiters or safety instructions are implemented within the skill to isolate user-provided data from system instructions. 3. Capability inventory: The skill initiates detail page generation tasks and retrieves results from the remote IMIVA platform via scripts/imiva_mcp.py. 4. Sanitization: While inputs are structured in JSON, no semantic validation or filtering of user-provided text is performed locally before transmission.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:02 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-reference-detail-page