customer-whisperer

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 1: "Collect Tickets" and the Integration Points table) explicitly ingests and analyzes user-generated support content from third-party sources like Intercom, Email, and Discord, which the agent reads and uses to generate drafts and action items—allowing untrusted content to influence behavior.