smtp2go-automation
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill directs users to configure an external MCP server at 'https://rube.app/mcp'. Although this is the core mechanism of the skill, the endpoint is a third-party service that does not belong to the list of trusted organizations.
- [DATA_EXFILTRATION] (LOW): Because the Rube MCP acts as a proxy between the agent and the Smtp2go API, sensitive communication data (such as email bodies and recipient details) is processed by the external service provider.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes data from an external service (Smtp2go), which constitutes a vulnerability surface. 1. Ingestion points: Data returned from Smtp2go tools (e.g., email logs, message content). 2. Boundary markers: Absent; the instructions do not provide delimiters or warnings to ignore instructions within the retrieved data. 3. Capability inventory: Includes execution of discovered tools and remote workbench operations. 4. Sanitization: None; the skill does not specify any validation or sanitization for content retrieved from the external API.
Audit Metadata