formio

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to call Form.io via the Membrane CLI (e.g., "membrane action run" for actions like list-submissions/get-form and "membrane request CONNECTION_ID /path/to/endpoint"), which will ingest user-generated/public Form.io content (forms and submissions) that the agent is expected to read and could materially influence subsequent actions.