keyword-research

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

• Third-party content exposure detected (high risk: 0.90). The workflow explicitly requires pulling data from public third-party sources—e.g., autocomplete/"People Also Ask" queries, Google Trends/serp metrics, and competitor sites (examples: intercom.com, zendesk.com) for gap analysis—so the agent must fetch and interpret untrusted public web content as part of normal operation.