Intercom Automation
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and acts on untrusted user-generated inbound messages (see "CUSTOMER CONVERSATION FLOW", the routing_rules with message_contains, and bot_responses sections) from Intercom users, and uses their content to drive routing, ticket creation, notifications, and automated replies, which could enable indirect prompt injection.
Audit Metadata