sendgrid-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of a remote Model Context Protocol (MCP) server at
https://rube.app/mcp. This connects the agent to external infrastructure hosted on the Rube platform to facilitate tool execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the SendGrid API which could contain malicious instructions designed to influence agent behavior.
- Ingestion points: External data is ingested via
SENDGRID_RETRIEVE_ALL_LISTS(list metadata),SENDGRID_GET_CONTACTS_BY_EMAILS(contact records), andSENDGRID_FILTER_ALL_MESSAGES(email activity/content logs). - Boundary markers: The instructions do not define delimiters or warnings to treat external data as untrusted content.
- Capability inventory: The skill possesses sensitive capabilities including sending emails (
SENDGRID_CREATE_SINGLE_SEND), modifying contact databases (SENDGRID_ADD_OR_UPDATE_A_CONTACT), and deleting resources (SENDGRID_REMOVE_LIST_AND_OPTIONAL_CONTACTS). - Sanitization: There are no instructions for sanitizing or escaping content retrieved from SendGrid before it is integrated into the agent's context.
Audit Metadata