Mailchimp Automation

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data and interpolates it into templates without sufficient protection.
  • Ingestion points: The skill processes untrusted data from audience lists, campaign content, and automation triggers, including user-provided fields such as subject_line, preview_text, from_name, and template variables like {{first_name}} and {{product_name}} defined in SKILL.md.
  • Boundary markers: No delimiters or 'ignore embedded instructions' warnings are implemented to protect the agent when interpolating external data into email templates or campaign settings.
  • Capability inventory: The skill utilizes email-mcp tools (mailchimp_campaign, mailchimp_audience, mailchimp_automation, mailchimp_reports) to interact with the Mailchimp API, allowing it to create, configure, and send email campaigns and manage subscriber data based on the ingested content.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of external input fields before they are processed or used in generated email content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:21 AM