klaviyo-automation
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to call KLAVIYO_GET_CAMPAIGN_MESSAGE (and include 'template') to retrieve and read HTML/text campaign emails and SMS stored in Klaviyo—user-generated, third-party content—which the agent is expected to inspect as part of managing campaigns, creating a clear path for indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires contacting https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS/RUBE_MANAGE_CONNECTIONS) to fetch current tool schemas that directly determine the agent's tool prompts/instructions, and that external content is a required dependency.
Audit Metadata