customer-support-ops

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

• Third-party content exposure detected (high risk: 0.80). The skill's triage automation and auto-response workflows (see references/triage-automation.md and the SKILL.md "Triage Automation" / "Auto-response rules" sections) explicitly ingest and act on untrusted, user-generated ticket content (subject/body, URLs, keywords) to set priorities, route tickets, and trigger macros or automated actions, so third-party content can directly influence agent decisions and tool use.