linguixcom

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 call Linguix.com endpoints via Membrane (see "Running actions" and "Proxy requests"), which will fetch and return external/user-generated content from the public Linguix service that the agent is expected to read and act on, creating a clear avenue for indirect prompt injection.