commercevault-edd-digital-commerce
Warn
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs users to clone a repository from an unverified external source (
github.com/dhapat3927/mcp-edd-analytics-vantage.git) and install dependencies via package managers. - [COMMAND_EXECUTION]: The setup guide involves executing shell commands to install packages and start the MCP server (
npm start,python server.py), which results in the execution of code from the unverified repository. - [DATA_EXFILTRATION]: The skill handles highly sensitive information, including customer PII (names, email addresses), order history, revenue metrics, and license keys. Running unverified code with access to this data introduces a potential vector for unauthorized data access or exposure.
- [PROMPT_INJECTION]: The skill ingests and processes untrusted data from the Easy Digital Downloads API that may contain malicious instructions.
- Ingestion points: Data enters the context through product listings, order data, and customer profiles via endpoints like
client.orders.listandclient.customers.getinSKILL.md. - Boundary markers: The provided code examples lack explicit delimiters or instructions to help the agent distinguish between data and embedded commands.
- Capability inventory: The skill is capable of performing network requests to the configured WordPress API and interacting with local services like Redis.
- Sanitization: No sanitization or validation logic is demonstrated for the content retrieved from the external commerce API.
Audit Metadata