mailchimp-automation

Warn

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external, third-party MCP server endpoint: https://rube.app/mcp. This community-provided service handles tool execution and data proxying, which may expose sensitive operational data to an external entity.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by processing untrusted external data during campaign creation and subscriber management.
  • Ingestion points: HTML content provided to MAILCHIMP_SET_CAMPAIGN_CONTENT and subscriber data retrieved via MAILCHIMP_LIST_MEMBERS_INFO.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the workflows.
  • Capability inventory: The skill possesses high-impact capabilities including sending live email campaigns (MAILCHIMP_SEND_CAMPAIGN) and managing account connections (RUBE_MANAGE_CONNECTIONS).
  • Sanitization: There is no mention of sanitization, escaping, or validation for the HTML content or subscriber metadata being processed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 15, 2026, 05:41 PM
Security Audit — agent-trust-hub — mailchimp-automation