customer-support-integration
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documentation and accompanying evaluation files focus on legitimate customer support integration workflows. It includes code snippets for automated ticket creation, routing, and order context injection using well-known services such as Zendesk, Intercom, and Gorgias.- [INDIRECT_PROMPT_INJECTION]: The skill implements endpoints that ingest untrusted data from helpdesk webhooks and query parameters (Ingestion points: applyTicketRouting, getZendeskContext). While boundary markers are not present in the provided snippets, the skill utilizes capabilities such as database access and network requests to well-known services (Capability inventory: db.customers, fetch). The skill addresses these risks by instructing developers to implement HMAC verification and data normalization (Sanitization: HMAC check, toLowerCase email normalization).- [CREDENTIALS_UNSAFE]: No hardcoded credentials or unsafe secret handling patterns were found. The skill emphasizes best practices by instructing users to use environment variables and avoid client-side exposure of API tokens.
Audit Metadata