Omnisend Automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required workflow interacts with Omnisend contact and marketing management tools via Composio, which ingest contacts, orders, and customer data that can contain outsider-authored text/payloads.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external MCP server URL (https://rube.app/mcp) for connection and tool execution, constituting an operational inbound dependency with unknown or weak provenance.