klaviyo-automation

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external MCP server endpoint: https://rube.app/mcp. This is the intended delivery mechanism for the skill's capabilities and originates from the tool provider's infrastructure.
  • [PROMPT_INJECTION]: As the skill is designed to retrieve and inspect marketing content, it possesses an inherent surface for indirect prompt injection.
  • Ingestion points: Campaign message bodies, email subjects, and template content retrieved via KLAVIYO_GET_CAMPAIGN_MESSAGE and KLAVIYO_GET_CAMPAIGNS (SKILL.md).
  • Boundary markers: No specific delimiters are used to wrap the untrusted campaign content before the agent processes it.
  • Capability inventory: The agent can list, read, and monitor Klaviyo marketing campaigns and send jobs.
  • Sanitization: No explicit sanitization or filtering of marketing content is described; the skill relies on the agent's native safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 07:22 PM
Security Audit — agent-trust-hub — klaviyo-automation