slite

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly accesses and reads user-generated Slite documents via the Membrane proxy (see "Use when the user wants to interact with Slite data" and the "Proxy requests" / membrane request CONNECTION_ID examples in SKILL.md), so untrusted third-party content can be ingested and could influence actions.