ticket-triage

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Workflow step 1 explicitly ingests raw customer tickets (subject, body, attachments, and extracted URLs) — untrusted user-generated content — which the agent must read and use to determine category, priority, routing, and draft responses, creating a clear vector for indirect prompt injection.