activecampaign-automation

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses an attack surface for indirect prompt injection via data processed from ActiveCampaign.
  • Ingestion points: Contact data (names, emails, organization) retrieved via ACTIVE_CAMPAIGN_FIND_CONTACT.
  • Boundary markers: Absent; no instructions to ignore embedded commands in CRM data.
  • Capability inventory: The skill can create contacts, modify tags, manage list subscriptions, and enroll contacts in automations via the MCP toolset.
  • Sanitization: None specified for the data retrieved from external API responses.
  • External Downloads (LOW): The skill directs users to add https://rube.app/mcp as an MCP server. While this is the primary purpose of the skill, it introduces a dependency on an external, non-whitelisted third-party service.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:18 AM