gohighlevel

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

• Third-party content exposure detected (high risk: 0.80). The skill uses the Membrane CLI to fetch and read user-generated data from the third-party GoHighLevel service (see "Working with GoHighLevel" and the "Popular actions" list including get-conversation, list-contacts, forms, blog posts), so the agent will ingest untrusted third-party content that could influence subsequent actions.