Zendesk Automation

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, unauthorized network access, or hardcoded credentials were detected. The skill is configuration-based and uses established MCP server tools.
  • [PROMPT_INJECTION]: The skill processes untrusted data from customer support requests, which represents an indirect prompt injection surface.
  • Ingestion points: Support requests and ticket data (documented in the input section of SKILL.md).
  • Boundary markers: None present; the skill interpolates ticket data directly into response templates.
  • Capability inventory: Ticket creation, modification, and search via helpdesk-mcp tools.
  • Sanitization: No sanitization logic for external ticket content is specified in the provided configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:21 AM