mailchimp-automation
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of a remote MCP server located at
https://rube.app/mcp. This introduces a dependency on an external service for the execution of all Mailchimp-related tools. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection vulnerabilities due to the handling of external content in marketing workflows.
- Ingestion points: Untrusted data enters the agent context through the
htmlparameter in theMAILCHIMP_SET_CAMPAIGN_CONTENTtool and via subscriber profile data inMAILCHIMP_ADD_OR_UPDATE_LIST_MEMBER. - Boundary markers: The skill documentation does not define or recommend the use of boundary markers or instructions to ignore embedded commands within the campaign content or subscriber data.
- Capability inventory: The agent is granted significant capabilities, including the ability to send live email campaigns to audience lists (
MAILCHIMP_SEND_CAMPAIGN) and modify subscriber records. - Sanitization: There is no evidence of sanitization, escaping, or validation being performed on the HTML content or subscriber metadata before it is interpolated into tool parameters or processed by the agent.
Audit Metadata