sendgrid-automation

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to add an external MCP server endpoint (https://rube.app/mcp) to their client configuration to function.
  • [DATA_EXFILTRATION]: The skill manages sensitive data, including contact lists (emails, phone numbers) and marketing campaign details, which are transmitted to the external MCP server and SendGrid infrastructure.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its interaction with untrusted external data.
  • Ingestion points: Untrusted content enters the agent context via contact imports (SENDGRID_IMPORT_CONTACTS, SENDGRID_ADD_OR_UPDATE_A_CONTACT) and email body parameters (SENDGRID_CREATE_SINGLE_SEND).
  • Boundary markers: There are no specific instructions or delimiters mentioned to prevent the agent from following instructions embedded within the processed email content or contact metadata.
  • Capability inventory: The skill possesses extensive capabilities including sending marketing emails, managing sender identities, and modifying contact databases.
  • Sanitization: The skill lacks explicit sanitization or validation logic for the content it processes before passing it to the SendGrid API tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:56 AM