surveymethods

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md) explicitly instructs the agent to use Membrane commands like "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint" to fetch SurveyMethods data (surveys, responses, contacts) from the external SurveyMethods API, which is user-generated/untrusted content that the agent will read and can influence subsequent actions.