The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which presents an attack surface for indirect prompt injection.
Ingestion points: Processes Audience lists, Campaign content, and Automation triggers in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded prompts within data fields are provided in the configuration snippets.
Capability inventory: The skill utilizes email-mcp tools (mailchimp_campaign, mailchimp_audience, etc.) which involve network operations (Mailchimp API interaction) and the ability to send communications.
Sanitization: No explicit sanitization, validation, or escaping of the interpolated data fields (e.g., {{first_name}}, {{product_name}}, or audience-derived content) is mentioned.

Mailchimp Automation