activecampaign-automation

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires adding a remote MCP server from https://rube.app/mcp, which provides the agent with tools hosted on an external domain.\n- [DATA_EXFILTRATION]: Facilitates the transmission of sensitive CRM data, such as emails and phone numbers, to the external https://rube.app/mcp endpoint for automation processing.\n- [PROMPT_INJECTION]: Contains a surface for indirect prompt injection by ingesting untrusted contact data from ActiveCampaign and utilizing it in subsequent toolkit operations.\n
  • Ingestion points: External contact data retrieved from ActiveCampaign tools such as ACTIVE_CAMPAIGN_FIND_CONTACT (SKILL.md).\n
  • Boundary markers: Absent. No delimiters or instructions are used to distinguish external data from system prompts.\n
  • Capability inventory: Tool sequence for managing contacts, tags, subscriptions, and automations (SKILL.md).\n
  • Sanitization: Absent. There is no evidence of validation or filtering for data retrieved from the CRM.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 07:32 AM
Security Audit — agent-trust-hub — activecampaign-automation