screendesk

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

• Third-party content exposure detected (high risk: 0.80). The skill's core workflow instructs using Membrane to run actions and proxy requests against the Screendesk API (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint"), which will retrieve user-generated customer/ticket content from a third-party system that the agent is expected to read and act on, exposing it to potentially untrusted instructions.