ecommerce-ozon-product-detail

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The Python script performs network requests to an external API endpoint defined by the NEXSCOPE_PROXY_BASE environment variable to retrieve product details. This behavior is documented and aligns with the skill's primary function of providing marketplace research data.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a Python script (scripts/ozon_product_detail.py) and use shell utilities like jq to process the resulting JSON files. These operations are restricted to the local environment and are intended for data processing.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external marketplace API (product titles, descriptions, etc.) and processes it for display. While this represents a potential injection surface where malicious content in a product card could attempt to influence the agent, the skill defines clear display rules and processing boundaries that mitigate this risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:13 AM
Security Audit — agent-trust-hub — ecommerce-ozon-product-detail