case-study-builder

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly requires incorporating “Customer quote (in their words)” and “Company profile / Challenge / Solution / Results” from the customer, which are outsider-authored free-form text provided by a non-operating-user party at runtime into the agent’s LLM context.