signals-scout-surveys

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

• Third-party content exposure detected (high risk: 0.95). The skill ingests outsider-authored free text from open-text survey responses stored in events (via execute-sql open-text pull that selects the response text from properties keys like $survey_response_<question_id> / $survey_response), and then clusters/quotes that text into the agent’s LLM context for theme aggregation.