stock-reconcile

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install and run the marketplaces-mcp-ru package using uvx. This is a third-party dependency required for the skill's core functionality.
  • [COMMAND_EXECUTION]: Provides specific instructions for the user to execute the command uvx marketplaces-mcp-ru in their terminal to set up the necessary MCP server environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from several external marketplace APIs, which constitutes an attack surface for indirect prompt injection.
  • Ingestion points: Data is gathered via tools such as wb_stats_stocks, wb_analytics_warehouse_remains, ozon_stocks_info, ozon_stocks_by_warehouse_fbs, ym_get_offer_mappings, avito_get_stocks_info, wb_stats_sales, and ozon_analytics_data (identified in SKILL.md).
  • Boundary markers: The instructions do not define explicit boundary markers or include warnings to ignore instructions embedded within the marketplace data.
  • Capability inventory: The skill has capabilities to read business data and can potentially perform write operations (stock updates) if the user confirms the action.
  • Sanitization: There is no mention of sanitization, filtering, or validation of the data retrieved from external platforms before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:15 PM