sales-export

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to execute the command uvx marketplaces-mcp-ru to run the required MCP server. This involves fetching and executing a package from a Python package registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by ingesting and processing data from external marketplace APIs.
  • Ingestion points: Data is fetched via methods like wb_stats_sales, wb_stats_orders, ozon_analytics_data, ozon_finance_realization, and ym_get_orders from Wildberries, Ozon, and Yandex Market.
  • Boundary markers: None identified in the prompt templates.
  • Capability inventory: The skill processes this data to generate summaries, tables, and trend analyses.
  • Sanitization: No specific sanitization or filtering of API responses is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:15 PM