privacy-policy

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly instructs the agent to "Visit the product website" (Workflow step 1) and to use the user-provided product URL to identify data collection and third-party integrations, meaning it ingests arbitrary public website content that can directly influence policy drafting and tool decisions.