slottable

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflows (e.g., "membrane action run" and especially "membrane request CONNECTION_ID /path/to/endpoint" which proxies to the Slottable API) fetch and ingest data from a third‑party service that can contain user-generated/untrusted content that the agent is expected to read and which could influence subsequent actions.