klaviyo-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server located at https://rube.app/mcp for tool execution.
  • [PROMPT_INJECTION]: The skill processes untrusted data from Klaviyo campaign messages, creating a surface for indirect prompt injection.
  • Ingestion points: Campaign message content (subject, body) retrieved via KLAVIYO_GET_CAMPAIGN_MESSAGE in SKILL.md.
  • Boundary markers: Absent; the instructions do not define delimiters for external data.
  • Capability inventory: The skill performs read and monitoring operations on campaign data via Rube MCP tools.
  • Sanitization: Absent; the instructions do not include logic to sanitize or filter the content of campaign messages before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — klaviyo-automation