commercevault-edd-mcp-server

Fail

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation directs users to clone a repository from an untrusted GitHub account ("https://github.com/dhapat3927/mcp-edd-analytics-vantage.git").
  • [REMOTE_CODE_EXECUTION]: The installation process requires the user to execute the downloaded source code ("node server.js" or "python server.py") to function as an MCP server.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external Easy Digital Downloads APIs, providing a potential injection surface.
  • Ingestion points: Product catalog data, customer orders, and sales analytics retrieved from the EDD REST API.
  • Boundary markers: None identified; implementation snippets show direct interpolation of API data into processing logic.
  • Capability inventory: The skill performs network operations and data transformation for reporting to the AI agent.
  • Sanitization: No explicit validation or sanitization of the ingested API data is demonstrated in the provided code examples.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 16, 2026, 10:42 PM
Security Audit — agent-trust-hub — commercevault-edd-mcp-server