sendgrid-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external Model Context Protocol (MCP) server at https://rube.app/mcp to access the SendGrid toolkit.
  • [DATA_EXFILTRATION]: The skill facilitates the management, retrieval, and export of sensitive Personally Identifiable Information (PII), including contact emails, phone numbers, and physical addresses stored within SendGrid.
  • [PROMPT_INJECTION]: There is a surface for indirect prompt injection as the agent processes external data from SendGrid (such as contact identifiers, email templates, and campaign content) which could contain malicious instructions targeting the LLM.
  • Ingestion points: SendGrid contact lists, email HTML body content, and CSV files imported via SENDGRID_IMPORT_CONTACTS.
  • Boundary markers: The instructions do not define delimiters or protective boundary markers to separate external data from core logic.
  • Capability inventory: The skill possesses capabilities for sending emails, creating marketing campaigns, and modifying contact databases via the rube MCP.
  • Sanitization: No explicit sanitization, validation, or escaping of ingested email content or contact metadata is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:34 AM