api-void

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 use Api Void (via the Membrane CLI) to "send requests to any API endpoint" and run actions such as "Check URL Reputation" and "Get Site Trustworthiness" that fetch and return data from public websites/URLs, which the agent will read and could influence subsequent decisions.