wildberries-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the MCP server source code and dependencies from the author's GitHub repository (ilyautov/wildberries-mcp-ru) during the installation process.
  • [COMMAND_EXECUTION]: Provides instructions for installing and running the server using the uvx command-line tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection by processing external data from the Wildberries API.
  • Ingestion points: API response content retrieved via wb_call_method.
  • Boundary markers: None present.
  • Capability inventory: Capabilities include searching methods, describing API endpoints, and executing API calls (read/write).
  • Sanitization: Instructions mandate that the agent must show the request body to the user and wait for explicit confirmation before executing any write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:16 PM
Security Audit — agent-trust-hub — wildberries-mcp